CN113723191B

CN113723191B - Road congestion prediction method, location-based service providing method, and program product

Info

Publication number: CN113723191B
Application number: CN202110871171.1A
Authority: CN
Inventors: 刘羽飞
Original assignee: Autonavi Software Co Ltd
Current assignee: Autonavi Software Co Ltd
Priority date: 2021-07-30
Filing date: 2021-07-30
Publication date: 2024-03-29
Anticipated expiration: 2041-07-30
Also published as: CN113723191A

Abstract

The embodiment of the disclosure discloses a road congestion prediction method, a position-based service providing method and a program product, wherein the method comprises the following steps: acquiring a current road traffic characteristic of a current period of a target road and a road congestion image characteristic of the target road; predicting congestion occurrence time and congestion trend of the target road based on the current road traffic characteristics and the road congestion portrait characteristics; optimizing the congestion occurrence time and/or congestion tendency based on a combination of one or more of the attributes of the target road, the current road condition of the associated road of the target road, and the predicted historical traffic characteristics of the congestion occurrence time. According to the technical scheme, the traffic pressure of the congested road can be relieved, the travel time cost can be saved for the user, and the travel experience of the user is improved.

Description

Road congestion prediction method, location-based service providing method, and program product

Technical Field

The disclosure relates to the technical field of dynamic traffic, in particular to a road congestion prediction method, a position-based service providing method and a program product.

Background

With the continuous expansion of urban scale and the continuous increase of private car holding quantity, traffic jam becomes a problem which is not negligible for urban management.

The existing dynamic traffic (real-time traffic) system can predict road conditions (congestion, creep or smoothness) and provide the predicted road conditions for relevant service systems such as navigation calculation or traffic management. Taking the navigation road service as an example, the navigation road service can avoid the road (the congested road) in the congested state based on the predicted road condition when planning the navigation route, so that the vehicles entering the congested road section can be reduced, the traffic pressure of the congested road can be relieved, on the other hand, the travel time cost of the user can be saved, and the travel experience of the user can be improved.

Therefore, how to accurately predict road conditions is one of the technical problems that those skilled in the art are required to continuously solve and optimize.

Disclosure of Invention

The embodiment of the disclosure provides a road congestion prediction method, a position-based service providing method and a program product.

In a first aspect, an embodiment of the present disclosure provides a method for predicting road congestion, where the method includes:

acquiring a current road traffic characteristic of a current period of a target road and a road congestion image characteristic of the target road;

Predicting congestion occurrence time and congestion trend of the target road based on the current road traffic characteristics and the road congestion portrait characteristics;

optimizing the congestion occurrence time and/or congestion tendency based on a combination of one or more of the attributes of the target road, the current road condition of the associated road of the target road, and the predicted historical traffic characteristics of the congestion occurrence time.

Further, predicting the congestion occurrence time and the congestion tendency of the target road based on the current road traffic characteristics and the road congestion portrait characteristics includes:

and comparing the similarity between the current road traffic characteristic and the road congestion image characteristic within a set time length from the current time, if the similar road congestion image characteristic is compared, predicting the congestion occurrence time of the target road based on the road congestion image characteristic, and taking the congestion trend corresponding to the road image characteristic as the predicted congestion trend of the target road.

Further, optimizing the congestion occurrence time and/or congestion tendency based on a combination of one or more of the attributes of the target link, the current road condition of the associated link of the target link, and the predicted historical traffic characteristics of the congestion occurrence time, includes:

Acquiring the attribute of the target road, wherein the attribute at least comprises: road grade;

acquiring the current road condition of an upstream road and/or a downstream road of the target road;

and correcting the congestion tendency of the target road according to the attribute of the target road, the current road condition of the upstream road and/or the downstream road of the target road and the predicted historical traffic characteristics of the congestion occurrence time, and the influence weight of the attribute, the current road condition and the historical traffic characteristics on the congestion tendency.

Further, the road congestion image features comprise road congestion image features of the target road before congestion, during congestion and/or after congestion dissipates; based on the current road traffic characteristics and the road congestion portrait characteristics, predicting the congestion occurrence time and the congestion trend of the target road comprises the following steps:

respectively comparing the similarity between the current road traffic characteristics and the road congestion image characteristics before congestion, during congestion and/or after congestion dissipation;

and taking the congestion trend corresponding to the most similar road congestion portrait characteristic in the road congestion portrait characteristic before congestion, in congestion and/or after congestion dissipation as the congestion trend of the target road, and predicting the congestion occurrence time of the target road based on the most similar road congestion portrait characteristic.

determining a characteristic day corresponding to the current time period;

carrying out similarity comparison on the current road traffic characteristics and the road congestion image characteristics corresponding to the characteristic days;

and determining the congestion trend corresponding to the road congestion portrait feature corresponding to the feature day with the largest similarity value as the congestion trend of the target road, and predicting the congestion occurrence time of the target road based on the road congestion portrait feature corresponding to the feature day with the largest similarity value.

determining one or more comparison periods of the current period; the comparison period comprises one or more congestion periods which are in a preset time range with the current period; the congestion time period is a time period corresponding to road congestion image characteristics;

carrying out similarity comparison on the current road traffic characteristics and road congestion image characteristics corresponding to the comparison period;

And determining the congestion trend corresponding to the road congestion portrait characteristic corresponding to the comparison period with the maximum similarity value as the congestion trend of the target road, and predicting the congestion occurrence time of the target road based on the road congestion portrait characteristic corresponding to the comparison period with the maximum similarity value.

screening out the road congestion image features with the similarity to the current road traffic features higher than a preset threshold value based on the similarity to the road congestion image features;

and predicting the congestion trend and the congestion occurrence time of the target road based on the screened road congestion image characteristics and the corresponding congestion time period and the proximity degree between the current time period.

Further, the congestion tendency includes a combination of one or more of:

the congestion stage, the congestion degree, the congestion predicted duration, the congestion predicted formation time and the confidence of the congestion tendency; wherein the congestion phase comprises one or more of congestion non-formation, congestion aggravation, congestion severity, daily congestion, congestion dissipation.

In a second aspect, in an embodiment of the present invention, a location-based service providing method is provided, where the method uses a congestion tendency predicted by the method in the first aspect to provide a location-based service for a served object, where the location-based service includes: navigation, map rendering, route planning.

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

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is configured to acquire current road traffic characteristics of a current time period of a target road and road congestion image characteristics of the target road;

the prediction module is configured to predict the congestion occurrence time and the congestion trend of the target road based on the current road traffic characteristics and the road congestion portrait characteristics;

and an optimization module configured to optimize the congestion occurrence time and/or congestion tendency based on a combination of one or more of the attributes of the target road, the current road condition of the associated road of the target road, and the predicted historical traffic characteristics of the congestion occurrence time.

In a fourth aspect, in an embodiment of the present invention, there is provided a location-based service providing apparatus for providing a location-based service to a served object using a congestion tendency predicted by the road congestion prediction apparatus, the location-based service including: navigation, map rendering, route planning.

The functions may be implemented by hardware, or may be implemented by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the functions described above.

In one possible design, the structure of the above apparatus includes a memory for storing one or more computer instructions for supporting the above apparatus to perform the corresponding method, and a processor configured to execute the computer instructions stored in the memory. The apparatus may further comprise a communication interface for the apparatus to communicate with other devices or a communication network.

In a fifth aspect, an embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored on the memory, where the processor executes the computer program to implement the method of any one of the above aspects.

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

In a seventh aspect, embodiments of the present disclosure provide a computer program product comprising computer instructions for implementing the method of any one of the above aspects when executed by a processor.

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

in the process of predicting the congestion tendency of the target road, the road congestion image characteristics of the target road are determined offline, so that the current road traffic characteristics of the target road are collected during real-time prediction, the similarity between the current road traffic characteristics and the road congestion image characteristics is compared, and the congestion tendency of the target road is predicted based on the comparison result of the similarity; in order to further improve the accuracy of the congestion tendency, the congestion tendency is optimized by using one or more of the attribute of the target road, the portrait characteristic of the current period, the current road condition of the associated road and the like. According to the embodiment of the disclosure, a complex real environment is shielded by utilizing a historical congestion aggregation logic in an offline process in a mode of combining offline prediction with online prediction, a result of periodic congestion of a road is directly imaged based on historical data, and finally, a historical experience that a machine model is difficult to learn, namely road congestion imaging characteristics, are formed; in the real-time prediction process, the road congestion image characteristics and the real-time road traffic characteristics are combined to predict the congestion occurrence time and the congestion trend of the road, the predicted congestion trend is optimized by means of the road attribute, the current road condition of the associated road, the historical traffic characteristics of the predicted congestion occurrence time and the like, the congestion condition of the road in a future period can be fed back accurately and in real time finally, the traffic pressure of the congested road can be relieved, the travel time cost can be saved for a user, and the travel experience of the user is improved.

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, taken in conjunction with the accompanying drawings. In the drawings:

FIG. 1 illustrates a flow chart of a method of road congestion prediction according to an embodiment of the present disclosure;

FIG. 2 illustrates an application diagram of a road congestion prediction method in a navigation scenario according to an embodiment of the present disclosure;

fig. 3 shows a block diagram of a road congestion prediction apparatus according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of an electronic device suitable for use in implementing a road congestion prediction method and/or a location-based service providing 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. In addition, for the sake of clarity, portions irrelevant to description of the exemplary embodiments are omitted in the drawings.

In this disclosure, it should be understood that terms such as "comprises" or "comprising," etc., are intended to indicate the presence of features, numbers, steps, acts, components, portions, or combinations thereof disclosed in this specification, and do not preclude the presence or addition of one or more other features, numbers, steps, acts, components, portions, or combinations thereof.

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

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

Fig. 1 shows a flowchart of a road congestion prediction method according to an embodiment of the present disclosure. As shown in fig. 1, the road congestion prediction method includes the steps of:

in step S101, a current road traffic characteristic of a current time period of a target road and a road congestion image characteristic of the target road are obtained;

in step S102, based on the current road traffic characteristics and the road congestion portrait characteristics, predicting congestion occurrence time and congestion tendency of the target road;

in step S103, the congestion occurrence time and/or congestion tendency is optimized based on a combination of one or more of the attribute of the target road, the current road condition of the associated road of the target road, and the predicted historical traffic characteristics of the congestion occurrence time.

In this embodiment, the road congestion prediction method may be run on a server. The links (links) may be one of the directional logic road units divided according to actual roads, each of which may have an independent road identification, and each of which may include an entrance and an exit. The target link may be any one of the links.

The current road traffic characteristic may be a road traffic characteristic on the target road acquired in real time. In some embodiments, the current road traffic characteristics may be obtained based on real-time traffic distribution information, navigation data returned by the navigation system, communication traffic of the vehicle, and the like. Road traffic characteristics may include, but are not limited to: the average traffic volume of the vehicle, the average traffic speed of the vehicle through the target link, the average traffic time of the vehicle through the target link, the vehicle volume distribution of different traffic speeds, the vehicle volume distribution of different traffic times, and the average vehicle volume expected to reach the target link within a preset time period. The traffic distribution of the vehicles passing through the target road may be, for example, a distribution of traffic speeds of vehicles passing through the target road in a plurality of traffic speed ranges, and the traffic speed ranges may include, but are not limited to, less than 10 km/h, 10-20 km/h, 20-40 km/h, 40-60 km/h, greater than 60 km/h, and the like. The transit time profile of the vehicles passing through the target link may be, for example, a profile of transit times of the vehicles passing through the target link over one or more transit time ranges, which may include, but are not limited to, less than 30 seconds, 30-60 seconds, 60-120 seconds, 120-180 seconds, 180-240 seconds, greater than 240 seconds, etc.

The road congestion image feature may be a traffic feature corresponding to a period of congestion of a target road, and may include, but is not limited to, an average traffic volume of vehicles, an average traffic speed of vehicles through the target road, an average traffic time of vehicles through the target road, a distribution of vehicle volumes at different traffic speeds, a distribution of vehicle volumes at different traffic times, and an average vehicle volume expected to reach the target road for a preset period of time.

In some embodiments, the road congestion image feature may also include the distribution of congestion batches and the transfer relationship of associated roads. The distribution of user batches may include, but is not limited to, the number of times congestion occurs within a preset period of time. The delivery of the associated link may include, but is not limited to, an identification of the associated link, a distance between the associated link and the target link, a delivery weight for the vehicle flow, a congestion creation offset (i.e., a difference between a time the associated link creates congestion and a time the target link creates congestion), a congestion dissipation offset (i.e., a difference between a time the associated link dissipates congestion and a time the target link dissipates congestion).

The congestion period may be one or more periods of time during which congestion periodically occurs on the target link as determined by statistically analyzing historical road condition data of the target link. The congestion period may be one or more time periods of the day.

In some embodiments, the road congestion image features are obtained as follows:

acquiring a congestion road and a congestion period corresponding to the congestion road based on the historical road condition information of the road in the historical period;

the method comprises the steps of aggregating congestion time periods corresponding to a congestion road according to a set congestion image time range, and generating congestion time characteristics of the congestion road in the congestion image time range, wherein the congestion time characteristics comprise: a pre-congestion formation time feature, a congestion duration feature, a congestion dissipation time feature;

and processing the road traffic characteristics of the congested roads according to the time in the congestion time characteristics to obtain road congestion image characteristics of corresponding time.

The historical time period may be a time period in days, including one day or continuous or discrete days.

The historical road condition information may refer to various information describing actual traffic conditions of each road in the historical period, and by way of example, the historical road condition information may include road condition states of each road in the historical period or some information capable of reflecting the road condition states, the road condition states may include a congestion state and a non-congestion state, and the non-congestion state may include a plurality of states such as a clear state and a buffer state. The historical road condition information reflecting the road condition state can include traffic speed or traffic time, and in general, the road condition state of each road is related to the traffic speed or traffic time of the vehicle on the road, and the traffic speed or traffic time of different roads can be mapped to different road condition states because the traffic speed requirements of different roads are different and the lengths of different roads are also different. Taking traffic information as an example of traffic speed, for suburban road link1, traffic states corresponding to traffic speeds [ 70-80 km/h ] are smooth, traffic states corresponding to traffic speeds [ 50-70 km/h ] are slow, and traffic states corresponding to traffic speeds [ 30-50 km/h ] are congested. For the urban central road link2, the road condition state corresponding to the passing speed [ 40-60 km/h ] is an unblocked state, the road condition state corresponding to the passing speed [ 30-40 km/h ] is a slow running state, and the road condition state corresponding to the passing speed [ 20-30 km/h ] is a congestion state.

The historical road condition information can be obtained based on the road condition information issued by the service system of the position in real time.

In the process of portraying the road, the congestion time periods corresponding to the congested road can be aggregated in the congestion image time range, the congestion of the congested road in the congestion image time range is determined to occur for several times, the congestion time characteristics corresponding to the several times of congestion are generated, and 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 feature and a congestion dissipation time feature, wherein the time corresponding to the time feature before congestion formation, the congestion duration feature and the congestion dissipation time feature is a continuous time, and the time before congestion formation, the time period during which congestion is continued and the time after congestion dissipation of the present congestion are respectively indicated. The congestion duration characteristic is a characteristic representing a congestion duration of the present congestion, such as a time at which the present congestion starts and a time at which the congestion ends, the pre-congestion formation time characteristic is a characteristic representing a time period before the present congestion starts, such as a time between the congestion start time and a first preset time period before the congestion start time, and the congestion dissipation time characteristic is a characteristic representing a time period after the present congestion ends, such as a time between the congestion end time and a second preset time period after the congestion end time.

Assuming that the congestion image time range is one day, aggregating congestion duration features corresponding to the congested roads on the day, and for the congested roads with the same road ID, combining each congestion period corresponding to the congested roads into one or more congestion duration features, for example, link1 corresponds to 7: 30-8: 30 and 17: 30-18: 30, each of the congestion duration characteristics may be extended forward and backward for a period of time, a first pre-set time period extending forward, e.g., 30 minutes, to obtain a pre-congestion-formation time characteristic, and a second pre-set time period extending backward, e.g., 30 minutes, to obtain a congestion dissipation time characteristic. This gives a first set of congestion time characteristics for link1 during the day: congestion pre-formation time feature 7: 00-7: 30, congestion duration feature 7: 30-8: 30, congestion relief time feature 8: 30-9: 30; a second set of congestion time characteristics: congestion pre-formation time feature 17: 00-17: 30, congestion duration feature 17: 30-18: 30, congestion relief time feature 18: 30-19: 30.

in some embodiments, the road congestion image feature refers to information that can describe the congestion condition of the road, such as the congestion occurrence probability, the congestion time, the congestion duration, or the traffic capacity when congested. The road congestion feature may include a road congestion image feature before congestion is formed, during congestion persisting, after congestion dissipates.

In the embodiment of the disclosure, in an offline case, the road congestion image feature may be predetermined based on the history data of the target road. In the online process of real-time prediction, the current road traffic characteristics of the target road can be collected in real time, and as can be known from the above description, the current road traffic characteristics correspond to the road congestion image characteristics obtained in advance. Thus, after the current road traffic characteristics on the target road are collected in real time, the current road traffic characteristics may be compared with the road congestion image characteristics. For example, the similarity between the average traffic speed of the vehicle passing through the target road in the current road traffic feature and the road congestion image feature, the similarity between the average traffic time of the vehicle passing through the target road, the similarity of the vehicle quantity distribution situation of different traffic speeds, the similarity of the vehicle quantity distribution situation of different traffic times, and/or the similarity of the average vehicle quantity expected to reach the target road within the preset time period may be compared, respectively. After the comparison, whether the current road condition of the target road is similar to the road congestion image features or not can be determined according to the comparison result, if so, whether the target road is congested in a period of time in the future or not can be predicted based on the road congestion image features, and if so, congestion tendency such as congestion duration and the like can be predicted. For example, the compared road congestion image features describe the characteristics of the target road before congestion, and based on the characteristics, the current situation of the target road before congestion can be determined, and the congestion tendency of the target road in a future period of time is that congestion is forming.

In some embodiments, the congestion tendency may include, but is not limited to, one or more of a congestion phase, a degree of congestion, an expected duration of congestion, a confidence in the congestion tendency; wherein the congestion phase includes a combination that may include, but is not limited to, one or more of congestion formation, congestion aggravation, congestion severity, daily congestion, congestion dissipation. The congestion occurrence time may be a time when the congestion of the target road is predicted, for example, a condition that the target road is currently in front of the congestion is predicted according to the road congestion image feature, and the road congestion time when the congestion of the target road is predicted based on the road congestion image feature.

It is considered that predicting the congestion tendency from only the comparison result between the current road traffic characteristic and the road congestion image characteristic of the target road may cause an inaccurate prediction result. Accordingly, embodiments of the present disclosure also propose ways to optimize the predicted congestion tendency.

In some embodiments, the congestion tendency of the target link may be optimized based on one or more combinations of attributes of the target link, current road conditions of the associated link of the target link, and historical traffic characteristics of predicted congestion occurrence times, and the like.

The attributes of the target road may include, but are not limited to, road width, whether there is traffic light, whether there is a highway expressway, daily traffic volume, free-flow speed, etc. The portrayal characteristics of the current time period may include, but are not limited to, weekdays, holidays, morning and evening peak hours, weekpeaks, night hours, etc. The associated links of the target link may include, but are not limited to, upstream links, downstream links, etc. of the target link vehicle flow.

The associated road of the target road may refer to each road through which a vehicle enters and exits from the target road and each road through which the vehicle passes before entering the target road in a road network within a preset geographical range. In some embodiments, current road condition information for the associated road may be obtained, which may include, but is not limited to, an average speed of travel of the vehicle through the associated road, an average time of travel of the vehicle through the associated road, a distribution of vehicle amounts for different speeds of travel, a distribution of vehicle amounts for different times of travel, and an average vehicle amount expected to reach the associated road for a preset period of time, etc. In some embodiments, the current traffic information may be determined based on traffic information published in real-time by the location-based service system.

In addition, an influence factor of the associated road and the target road may be predetermined. The impact factor may be used to represent the extent to which congestion formation or dissipation of the associated link affects congestion formation or dissipation of the target link. The congestion formation and dissipation of each target road are affected by the associated road, and when the congestion is formed and dissipated, the transmission relation of the traffic flow is very important, the larger the traffic flow entering and exiting between the associated road and the target road is, the larger the influence factor is, and the smaller the distance between the associated road and the target road is, the larger the influence factor is, so the influence factor can be predetermined based on the traffic flow entering and exiting between the associated road and the target road, the distance between the associated road and the target road, and the like. It should be noted that, the associated road may be separated from the target road by one or more other roads, or may be directly adjacent to the target road, when the associated road is adjacent to the target road, the distance from the exit of the associated road to the entrance of the target road is 0, and when the associated road may be separated from the target road by one or more other roads, the distance between the associated road and the target road is the sum of the lengths of the one or more other roads.

In some embodiments, the historical traffic characteristics of the predicted congestion occurrence time may include, but are not limited to, characteristics such as the probability that the target link will typically experience congestion at that congestion occurrence time. In some embodiments, the historical traffic characteristics of congestion occurrence times may be represented as traffic characteristics that are prone to congestion during the day, traffic characteristics that are not prone to congestion, and so on. If the congestion tendency of the target road is predicted to be formed, the congestion occurrence time is night, the method has the history traffic characteristics that the congestion is not easy to occur, the attribute of the target road is a expressway, the current road condition of the related road is good, the phenomena of high traffic or carrier flow, low traffic speed, long traffic time and the like do not exist, the actual road condition of the target road is high in probability that the congestion does not exist, and a certain gap exists between the actual road condition and the predicted congestion tendency, so that the method can be correspondingly optimized, for example, the method can be used for adjusting the weight of factors used for predicting the congestion tendency. Illustrating: if the factors affecting the prediction of the congestion tendency comprise the similarity between the current road traffic characteristics and the road congestion portrait characteristics, the proximity degree between the current time period and the time period corresponding to the road congestion portrait characteristics and the like, the congestion tendency can be obtained by recalculating after adjusting the weights of the factors.

In an optional implementation manner of this embodiment, step S102, that is, a step of predicting a congestion occurrence time and a congestion tendency of the target road based on the current road traffic characteristic and the road congestion representation characteristic, further includes the following steps:

In this alternative implementation, the road congestion image features may include, but are not limited to, image features corresponding to one or more time periods of the day in which congestion is likely to occur, respectively. In order to improve the prediction efficiency and accuracy, the current image feature of the current time may be compared with one or more road congestion image features within a set time length from the current time in one day, where the set time length may be set in advance based on experience or predicted actual requirements, and is not limited in particular. If the current time is compared with the road congestion image characteristics of a certain period of time, predicting the congestion trend and the congestion occurrence time of the target road based on the road congestion image characteristics which are similar. In some embodiments, the congestion tendency corresponding to the more similar road congestion portrait feature may be used as the congestion tendency of the target road, and the congestion occurrence time of the target road, in which congestion will occur, is predicted based on the congestion period corresponding to the road portrait feature in one day. For example, the more similar road congestion image feature corresponds to the image feature before the target road is congested, and the image feature before the congestion is separated from the image feature in the target congestion by N minutes, the congestion of the target road after N minutes can be predicted, so that the predicted congestion occurrence time of the target road can be the time obtained by adding N minutes to the current time.

In an optional implementation manner of this embodiment, step S103, that is, a step of optimizing the congestion occurrence time and/or congestion tendency based on one or more combinations of the attribute of the target road, the current road condition of the associated road of the target road, and the predicted historical traffic characteristics of the congestion occurrence time, further includes the steps of:

In this alternative implementation, the attributes of the target link may include, but are not limited to, link class, which may be partitioned based on, for example, link width, whether there is traffic light, whether there is an expressway or expressway, daily traffic and free-flow speed, and the like.

The associated links of the target link may include upstream links and/or downstream links. In general, the congestion status of the upstream road and the downstream road is transmitted to the target road, so that the congestion tendency of the target road can be corrected based on the current road condition information of the upstream road and/or the downstream road. The current road condition information of the upstream road and the downstream road can be the current actual road condition, and can be determined based on the road condition information issued by the position-based service system in real time and/or navigation data in the position-based service system. For example, it is predicted in real time that the congestion tendency of the target road will not form congestion in a future period of time, and the current road condition information of the downstream road is congestion, so that it can be determined that the congestion condition of the downstream road may be transmitted to the target road in a future period of time based on the congestion tendency, and therefore the congestion tendency can be corrected based on the current road condition of the upstream road and the downstream road, the current road condition of the associated road of the target road, and the historical traffic characteristics of the predicted congestion occurrence time, for example, the congestion tendency can be corrected to the congestion stage where the congestion tendency is currently located to form congestion. It will be understood, of course, that the above examples are for illustration only, and that other factors such as the nature of the target road, the history of traffic characteristics, etc. may also be considered in the actual correction process to influence the congestion tendency.

In some embodiments, in the process of optimizing the congestion tendency of the predicted target road, the attribute of the target road, the current road condition of the upstream road and/or the downstream road of the target road, and the history traffic characteristics of the predicted congestion occurrence time may be used as influence factors affecting the congestion tendency, and different influence weights may be given to the influence factors in advance, and after the congestion tendency of the target road is predicted, the congestion tendency of the target road may be corrected by acquiring the influence factors in the current period and based on the influence factors and the influence weights thereof.

In an optional implementation of this embodiment, the road congestion image feature includes a road congestion image feature of the target road before congestion, during congestion, and/or after congestion dissipates; step S102, that is, a step of predicting congestion occurrence time and congestion trend of the target road based on the current road traffic characteristics and the road congestion portrait characteristics, further includes the following steps:

In this alternative implementation, the predetermined road congestion image features may include road congestion image features of three congestion phases, i.e., pre-congestion, during congestion, and after congestion dissipation, corresponding to the congestion period. When the similarities are compared, the current road traffic characteristics can be respectively compared with road congestion image characteristics before congestion, during congestion and/or after congestion dissipation in each congestion period, and the congestion trend of the target road is determined according to the comparison result. If the current road traffic characteristics of the target road are most similar to road congestion image characteristics of one of the pre-congestion, in-congestion and/or after-congestion dissipation stages of a certain congestion period, it may be preliminarily determined that the congestion tendency of the target road is similar to the one of the stages, for example, similar to the road congestion image characteristics of the pre-congestion, it may be preliminarily determined that the congestion tendency of the target road is a congestion formation stage, and congestion may be formed in a future period of time by the target road, so that the congestion tendency corresponding to the road congestion image characteristics of the pre-congestion may be determined as the congestion tendency of the target road, and the congestion occurrence time of the target road may be predicted based on the road congestion image characteristics.

determining a characteristic day corresponding to the current time period;

In this alternative implementation, the feature day may be descriptive information expressing the road traffic feature of the day in units of days. In some embodiments, the characteristic day may include, but is not limited to, working day, non-working day, holiday, summer holiday, cold holiday, etc., and may be specifically set according to the actual condition of the road, which is not limited herein.

In the embodiment of the disclosure, in order to accurately image a road, different road congestion image features can be obtained in advance for different feature days.

In some embodiments, in order to image a road in units of characteristic days, a strong connected subgraph may be respectively established based on one or more congestion periods of each day, one vertex of the strong connected subgraph represents a day corresponding to one congestion period, an edge of the strong connected subgraph represents an associated time period existing between two congestion periods in two days corresponding to two vertices, and the associated time period existing between the two congestion periods may refer to a coincidence time period exceeding a preset threshold value between the two congestion periods; the preset threshold may be 1/2 of the shorter of the two congestion periods; after the strong connected subgraph is established, road congestion image features corresponding to the congestion periods in one or more days with associated time periods can be aggregated by traversing the strong connected subgraph, so that road congestion image features corresponding to feature days can be obtained, and the road congestion image features corresponding to the feature days can also comprise average congestion starting time, average congestion duration, congestion occurrence days, confidence degree of congestion occurrence, deviation time of congestion formation time, deviation time of congestion dissipation time and the like.

In some embodiments, the road congestion image features acquired for feature days may also include, but are not limited to, start lot (the first time congestion in a workday), congestion duration, congestion occurrence days, congestion frequency, congestion formation bias, congestion end bias, and the like.

When the congestion tendency of the target road is predicted in real time, the current road traffic characteristics can be compared with the road congestion image characteristics in the characteristic days corresponding to the current time period in a similarity mode. For example, if the current period is a period on a working day, the current road traffic feature is compared with the road congestion image feature on the working day, if the current period is a period on a non-working day, the current road traffic feature is compared with the road congestion image feature on the non-working day, the congestion tendency corresponding to the road congestion image feature corresponding to the feature day with the largest similarity value is further determined as the congestion tendency of the target road, and the congestion occurrence time of the target road is predicted based on the road congestion image feature corresponding to the feature day with the largest similarity value. By the method, different days similar to the congestion situation on the road can be aggregated in advance to form the characteristic days, the corresponding road image features are obtained according to the characteristic days, the congestion tendency of the target road is predicted by utilizing the road image features corresponding to the characteristic days in the current period, and the prediction accuracy of the congestion tendency can be further improved.

determining one or more comparison periods of the current period; the comparison period comprises one or more congestion periods within a preset time range with the current period; the congestion time period is a time period corresponding to road congestion image characteristics;

In the optional implementation manner, in the process of forming the road congestion image feature, the starting time and the ending time of the actual congestion of each road in each day can be obtained by analyzing and screening the road condition information issued by the position-based service system in real time, and the congestion period of each road in each day, each week or each month can be obtained by carrying out statistical analysis on the starting time and the ending time. The congestion periods within a time frame may include one or more, for example, the congestion periods of a workday day may include early peak periods, late peak periods, and the like.

After the congestion period is determined, road congestion image features corresponding to the congestion period can be obtained based on the historical road condition information collected in the congestion period. In some embodiments, road congestion image features corresponding to different congestion periods can be acquired every day, and then the road congestion image features corresponding to different congestion periods in the feature day can be obtained by means of aggregation of the road congestion image features corresponding to the congestion periods in different days.

Congestion conditions between the same or similar time periods per day may be more similar, while congestion conditions between time periods farther apart may be less similar. Therefore, in the embodiment of the disclosure, in the process of real-time prediction, the current road traffic characteristics can be compared with the road congestion image characteristics of the same or similar time period in a similarity manner. The current road traffic characteristic is a characteristic of the current period, a time range can be preset, a congestion period which is in the same time range as the current period is determined to be the same or similar to the current period, further similarity comparison is carried out on the current road traffic characteristic and a road congestion image characteristic corresponding to the comparison period, a congestion trend corresponding to the road congestion image characteristic corresponding to the comparison period with the largest similarity value is determined to be the congestion trend of the target road, and the congestion occurrence time of the target road is predicted based on the road congestion image characteristic corresponding to the comparison period with the largest similarity value.

In some embodiments, the comparison period may be one or more congestion periods that are co-located with the current period on the same characteristic day.

In this alternative implementation, the current road traffic characteristics may be compared for similarity to road congestion image characteristics for multiple congestion periods. In the process of predicting the congestion tendency in real time, the road congestion image features with low similarity can be ignored, and the congestion tendency of the target road is predicted based on the road congestion image features with high similarity.

In some embodiments, a similarity threshold may be preset, road congestion image features with similarity greater than the similarity threshold may be screened out, and based on the principle that road conditions between two time periods close in time are relatively similar, the approach degree of the congestion time period of the screened road congestion image features and the current time period may be used as a factor of congestion trend prediction, so as to finally obtain the congestion trend of the target road. For example, although the current road traffic characteristic of the current period is similar to the road congestion image characteristic of a certain congestion period, if the distance between the current period and the congestion period is long, for example, the current period is night, and the congestion period is daytime, the road congestion image characteristic of the congestion period does not have a great reference to the current period, so the weight of the road congestion image characteristic corresponding to the congestion period is set to be small, or may be set to be 0.

In some embodiments, a calculation weight may be determined based on the proximity between the current time period and the congestion time period corresponding to the selected road congestion image feature, where the calculation weight of the congestion time period with higher proximity (i.e., two time periods overlap or have a shorter time distance) is set to be larger, and the calculation weight of the congestion time period with lower proximity (i.e., two time periods do not overlap and have a longer time distance) is set to be larger, and the congestion tendency of the target road is predicted by considering the congestion characteristics of the selected road congestion image feature. In some embodiments, the congestion characteristics of the road congestion image feature may include, but are not limited to, congestion phases (e.g., pre-congestion, during congestion, and after congestion dissipates) delineated by the road congestion image feature, congestion duration, average traffic speed during congestion, average traffic time, and the like.

In an alternative implementation of this embodiment, the congestion tendency includes a combination of one or more of the following:

In this alternative implementation, the congestion tendency of the target road is calculated by comparing the similarity between the current road traffic characteristics and the road congestion image characteristics. The current congestion stage may be determined based on the congestion stage corresponding to one or more sets of road congestion image features that are more similar to the current road traffic feature, e.g., one or more sets of road congestion image features that are most similar to the current road traffic feature are all pre-congestion features, then it may be determined that the target road is currently in the congestion formation stage. The current or future period of congestion stage also includes congestion aggravation, severe congestion, daily congestion, congestion dissipation, etc.

In the embodiment of the disclosure, the congestion tendency may further include a congestion degree, and the congestion degree may be determined based on an average transit time, an average transit speed, an average transit volume of the vehicles in the current road transit feature, an amount of the vehicles reaching the target road in a predicted period of time, and an average transit time, an average transit speed, an average transit volume of the vehicles before congestion, an amount of the vehicles reaching the target road in a predicted period of time, and the like.

The congestion tendency also includes the estimated duration of congestion and the estimated formation time of congestion, and the estimated duration of congestion may be calculated based on an estimated duration of a target link corresponding to a road congestion image feature (i.e., a road congestion image feature similar to a current road traffic feature) and an estimated duration of a target link corresponding to a road congestion image feature.

The congestion tendency also comprises the confidence of the congestion tendency, and the confidence of the congestion tendency (which can be also understood as the probability of congestion of the target road) can be calculated based on the calculated congestion degree of the target road, the current road condition state of the associated road and the corresponding congestion probability of the target road on the road congestion portrait feature. The current road condition of the associated road can be calculated based on the congestion degree of the associated road and the probability of congestion occurrence.

The following illustrates a way of calculating the congestion tendency:

the relative congestion level of the target link is calculated as follows:

v1＝speed/G1.speed，t1＝travel_time/G1.ttime，u1＝tp_users/G1.users，e1＝c10/G1.c10

level＝v1＊w1+t1＊w2+u1＊w3+e1＊w4，

where v1 represents a speed factor, speed represents an average traffic speed of the vehicle in the current road traffic feature, g1.speed represents an average traffic speed of the target road in the pre-congestion vehicle, t1 represents a time factor, travel_time represents an average traffic time of the vehicle in the current road traffic feature, g1.ttime represents an average traffic time of the target road in the pre-congestion vehicle, u1 represents a vehicle traffic factor, tp_users represents an average traffic of the vehicle in the current road traffic feature, g1.users represents an average traffic of the target road in the pre-congestion vehicle, e1 represents a vehicle estimated arrival factor, c10 represents an average vehicle amount estimated to reach the target road in 10 minutes in the current road traffic feature (the data may be determined based on navigation information in the navigation system), g1.c10 represents an average vehicle amount estimated to reach the target road in 10 minutes before congestion; level indicates the relative congestion degree of the target road, and w1, w2, w3 and w4 are preset weights.

Confidence in congestion tendency is calculated as follows:

relib＝level＊0.4+related_state＊0.3+hist_relib＊0.3

related_state＝∑w _i *relib _i *level _i

wherein, relib represents the confidence of the congestion tendency of the target road, level represents the congestion degree of the target road, related_state represents the current road condition state of the associated road, hist_relib represents the congestion confidence of the target road before congestion, and w _i Weight representing i-th associated road, relib _i Represents the congestion probability, level of the ith associated road _i Indicating the congestion degree of the i-th associated road. In some embodiments, the current road condition of the associated road may be calculated according to the actual road condition information, and the calculation manner may be similar to the above-mentioned prediction manner of the target road.

The estimated duration of congestion is calculated as follows:

offset＝(1-w6)＊hist_offset+w6＊related_offset

w6＝related_reib＊w5

where offset represents the predicted duration of the road trend of the predicted target road, hist_offset represents the trend duration of the target road before congestion, correlated_offset represents the congestion formation offset between the associated road and the target road, w6 represents the influence factor of the associated road, correlated_relib represents the congestion probability of the associated road, and w5 represents the weight of the congestion probability of the associated road.

In some embodiments, the congestion phase may be refined to 1/2 phase before congestion (which may be considered as half the period before congestion if the period before congestion is considered as a period of time), period of congestion, 1/4 phase before congestion (which may be considered as 3/4 the period before congestion if the period before congestion is considered as a period of time, i.e., impending congestion).

In an alternative implementation of this embodiment, the method further includes:

the road congestion image characteristics are predetermined.

The aggregation of the congestion periods corresponding to the congested roads generates the congestion time characteristics of the congested roads in the congestion image time range, including:

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

When only one alternative congestion duration characteristic is provided for the congestion road, the alternative congestion duration characteristic is used as the congestion duration characteristic for the congestion road;

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

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

The method comprises the steps of processing the road traffic characteristics of the congested roads according to the time in the congestion time characteristics to obtain road congestion image characteristics of corresponding time, and further comprises the following steps:

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

acquiring an influence factor between the associated road and the congested road based on the flow distribution and the distance between the associated road and the congested road;

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

establishing a strong communication subgraph based on the congestion duration characteristics corresponding to the congestion road every day, wherein one vertex of the strong communication subgraph represents a day corresponding to the congestion duration characteristics, and edges of the strong communication subgraph represent two congestion duration characteristics in two days corresponding to two vertices, wherein the two congestion duration characteristics have associated time periods, namely the overlapping time period between the two congestion duration characteristics exceeds a preset threshold; the preset threshold is 1/2 of the shorter of the two congestion duration periods;

Traversing the strong communication subgraph, and aggregating the road congestion image features corresponding to the 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 days on which the same type of congestion duration features are located, and average congestion starting time, average congestion duration, congestion occurrence days, congestion occurrence confidence, congestion formation time deviation duration and congestion dissipation time deviation duration corresponding to the same type of congestion duration features.

A location-based service providing method according to an embodiment of the present disclosure includes: the congestion tendency predicted by the road congestion prediction method provides a location-based service for a served object, wherein the location-based service comprises the following steps: navigation, map rendering, route planning.

In this embodiment, the location-based service providing method may be executed on a terminal, where the terminal is a mobile phone, ipad, computer, smart watch, vehicle, etc. The embodiments of the present disclosure may utilize the above-mentioned road congestion prediction method to predict a congestion tendency in a future period of time for any road or a preselected road, such as a hot road, and further may use the congestion tendency to provide more accurate location services, such as navigation services, path planning services, and/or map rendering services, for a served object during a location-based service.

The served object may be a cell phone, ipad, computer, smart watch, vehicle, robot, etc. When navigating, planning a path or rendering a road on a map for a served object, the congestion tendency of the road can be obtained based on the road congestion prediction method, so that a road section to be congested is avoided based on the congestion tendency when navigating or planning the path, the congested road section is selected to be dissipated or the congested road section is not present, and the congestion tendency of the road is rendered on the electronic map to play a role of warning when the map is rendered, and specific details can be seen from the description of the road congestion prediction method and are not repeated herein.

Fig. 2 illustrates an application diagram of a road congestion prediction method in a navigation scenario according to an embodiment of the present disclosure. As shown in fig. 2, in the offline stage, the prediction server uses offline information to image a road which is easy to be congested, and obtains a road congestion image feature of the congested road. The offline information can be obtained from a navigation server, and can include, but is not limited to, real-time road condition release information, navigation data, vehicle traffic information and the like for a congested road section in a congested period, road congestion image features are offline features, and the offline features of different congested roads are all stored in a feature library. The prediction server also obtains perception features by using offline feature aggregation, the perception features can be road congestion image features formed aiming at feature days, unexpected situations and the like, and the perception features are also stored in a feature library.

In the real-time stage, the prediction server collects real-time information, and the real-time information can also be obtained from the navigation server. The real-time information may include, but is not limited to, real-time traffic distribution information received in real-time, navigation data, vehicle traffic information, and the like. The prediction server extracts the current road traffic characteristics based on the real-time information, and further compares the similarity of the current road traffic characteristics on the same road with the road congestion image characteristics, and obtains the congestion tendency of the road based on the comparison result. In addition, the prediction server optimizes the congestion tendency based on the perception characteristics and the like to obtain the congestion tendency predicted in real time.

The prediction server sends the congestion tendency to the navigation server, and the navigation server adjusts the navigation path in real time based on the congestion tendency, so as to guide the vehicle to avoid the road which is about to generate congestion, and select the road which is free of congestion or about to be dissipated by the congestion to run.

The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure.

Fig. 3 shows a block diagram of a road congestion prediction apparatus according to an embodiment of the present disclosure. As shown in fig. 3, the apparatus may be implemented as part or all of an electronic device by software, hardware, or a combination of both. The road congestion prediction apparatus includes:

An obtaining module 301 configured to obtain a current road traffic characteristic of a current time period of a target road and a road congestion image characteristic of the target road;

a prediction module 302 configured to predict a congestion occurrence time and a congestion tendency of the target road based on the current road traffic characteristics and the road congestion representation characteristics;

an optimization module 303 configured to optimize the congestion occurrence time and/or congestion tendency based on a combination of one or more of the attributes of the target link, the current road condition of the associated link of the target link, and the predicted historical traffic characteristics of the congestion occurrence time.

In an alternative implementation of this embodiment, the prediction module includes:

and the first comparison submodule is configured to compare the similarity between the current road traffic characteristic and the road congestion image characteristic within a set time length from the current time, predict the congestion occurrence time of the target road based on the road congestion image characteristic if the similar road congestion image characteristic is compared, and take the congestion trend corresponding to the road congestion image characteristic as the predicted congestion trend of the target road.

In an optional implementation manner of this embodiment, the optimizing module includes:

the first obtaining submodule is configured to obtain the attribute of the target road, and the attribute at least comprises: road grade;

the second acquisition submodule is configured to acquire the current road condition of an upstream road and/or a downstream road of the target road;

the correcting sub-module is configured to correct the congestion tendency of the target road according to the attribute of the target road, the current road condition of the upstream road and/or the downstream road of the target road, the predicted historical traffic characteristics of the congestion occurrence time, and the influence weight of the attribute, the current road condition and the historical traffic characteristics on the congestion tendency.

In an optional implementation of this embodiment, the road congestion image feature includes a road congestion image feature of the target road before congestion, during congestion, and/or after congestion dissipates; the prediction module comprises:

a second comparison sub-module configured to compare the similarity between the current road traffic characteristics and the road congestion image characteristics before congestion, during congestion, and/or after congestion dissipation, respectively;

The first prediction submodule is configured to take a congestion trend corresponding to the road congestion portrait characteristic which is the most similar in the road congestion portrait characteristic before congestion, in congestion and/or after congestion dissipation as the congestion trend of the target road, and predict the congestion occurrence time of the target road based on the most similar road congestion portrait characteristic.

the first determining submodule is configured to determine a characteristic day corresponding to the current time period;

a third comparison sub-module configured to perform similarity comparison between the current road traffic characteristics and the road congestion image characteristics corresponding to the characteristic days;

and the second prediction submodule is configured to determine a congestion tendency corresponding to the road congestion portrait characteristic corresponding to the characteristic day with the largest similarity value as the congestion tendency of the target road, and predict the congestion occurrence time of the target road based on the road congestion portrait characteristic corresponding to the characteristic day with the largest similarity value.

A second determination submodule configured to determine one or more comparison periods of the current period; the comparison period comprises one or more congestion periods which are in a preset time range with the current period; the congestion time period is a time period corresponding to road congestion image characteristics;

a fourth comparison sub-module configured to perform similarity comparison between the current road traffic characteristics and road congestion image characteristics corresponding to the comparison period;

and the third prediction submodule is configured to determine a congestion tendency corresponding to the road congestion portrait characteristic corresponding to the comparison period with the largest similarity value as the congestion tendency of the target road, and predict the congestion occurrence time of the target road based on the road congestion portrait characteristic corresponding to the comparison period with the largest similarity value.

a screening sub-module configured to screen out the road congestion image features having a similarity to the current road traffic feature higher than a preset threshold based on the similarity to the road congestion image features;

And the second prediction submodule is configured to predict the congestion trend and the congestion occurrence time of the target road based on the screened road congestion image characteristics and the corresponding congestion time period and the proximity degree between the current time period.

The road congestion prediction device in this embodiment corresponds to the above road congestion prediction method, and specific details may be referred to the description of the road congestion prediction method above, which is not repeated here.

A location-based service providing apparatus according to an embodiment of the present disclosure may be implemented as part or all of an electronic device by software, hardware, or a combination of both. The location-based service providing apparatus provides a location-based service for a served object using the congestion tendency predicted by the road congestion prediction apparatus, the location-based service including: navigation, map rendering, route planning.

The location-based service providing device in this embodiment corresponds to the above location-based service providing method, and specific details thereof may be found in the description of the location-based service providing method above, which is not repeated herein.

As shown in fig. 4, the electronic device 400 includes a processing unit 401, which may be implemented as a processing unit such as CPU, GPU, FPGA, NPU. The processing unit 401 may execute various processes in the embodiments of any of the above methods of the present disclosure according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM403, various programs and data necessary for the operation of the electronic device 400 are also stored. The processing unit 401, ROM402, and RAM403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.

The following components are connected to the I/O interface 405: an input section 406 including a keyboard, a mouse, and the like; an output portion 407 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker, and the like; a storage section 408 including a hard disk or the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. The drive 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

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 embodiments of the present disclosure. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 409 and/or installed from the removable medium 411.

The flowcharts 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 flowchart or block diagrams may represent a module, segment, or 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 may be implemented by hardware. The units or modules described may also be provided in a processor, the names of which in some cases do not constitute a limitation of the unit or module itself.

As another aspect, the present disclosure also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the apparatus described in the above embodiment; or may be a computer-readable storage medium, alone, that is not assembled into a 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 of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by those skilled in the art that the scope of the invention referred to in this disclosure is not limited to the specific combination of features described above, but encompasses other embodiments in which any combination of features described above or their equivalents is contemplated without departing from the inventive concepts described. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Claims

1. A method of predicting road congestion, comprising:

acquiring a current road traffic characteristic of a current period of a target road and a road congestion image characteristic of the target road; the road congestion image features of the target road comprise road congestion image features of the target road in different congestion periods; the congestion time period is determined by carrying out statistical analysis on historical road condition data of the target road, and one or more time periods of congestion periodically occur on the target road; the road congestion image features comprise road congestion image features of the target road before congestion, during congestion and/or after congestion dissipation;

2. The method of claim 1, wherein predicting the congestion occurrence time and congestion tendency of the target link based on the current road traffic characteristics and the road congestion representation characteristics comprises:

And comparing the similarity between the current road traffic characteristic and the road congestion image characteristic within a set time length from the current time, if the similar road congestion image characteristic is compared, predicting the congestion occurrence time of the target road based on the road congestion image characteristic, and taking the congestion trend corresponding to the road congestion image characteristic as the predicted congestion trend of the target road.

3. The method of claim 1, wherein optimizing the congestion occurrence time and/or congestion tendency based on a combination of one or more of attributes of the target link, current road conditions of associated links of the target link, and historical traffic characteristics of the predicted congestion occurrence time comprises:

and correcting the congestion tendency of the target road according to the attribute of the target road, the current road condition of the upstream road and/or the downstream road of the target road, the predicted historical traffic characteristics of the congestion occurrence time, and the influence weight of the attribute, the current road condition and the historical traffic characteristics on the congestion tendency.

4. The method of claim 1 or 2, wherein predicting congestion occurrence time and congestion tendency of the target road based on the current road traffic characteristics and the road congestion representation characteristics comprises:

5. The method of claim 1 or 2, wherein predicting congestion occurrence time and congestion tendency of the target road based on the current road traffic characteristics and the road congestion representation characteristics comprises:

determining a characteristic day corresponding to the current time period;

6. The method of claim 1 or 2, wherein predicting congestion occurrence time and congestion tendency of the target road based on the current road traffic characteristics and the road congestion representation characteristics comprises:

7. The method of claim 1 or 2, wherein predicting congestion occurrence time and congestion tendency of the target road based on the current road traffic characteristics and the road congestion representation characteristics comprises:

8. The method of claim 1 or 2, wherein the congestion tendency comprises a combination of one or more of:

9. A method of providing location-based services, wherein the method provides location-based services to a served object using congestion tendency predicted by the method of any of claims 1-8, the location-based services comprising: navigation, map rendering, route planning.

10. A computer program product comprising computer instructions which, when executed by a processor, implement the method of any one of claims 1-9.