CN111986490A - Road condition prediction method and device, electronic equipment and storage medium - Google Patents

Abstract

The present application discloses a road condition prediction method, device, electronic device and storage medium, and relates to the technical field of intelligent transportation. The specific implementation scheme is: determine the historical road traffic information of the current time period in the historical period; determine the real-time road traffic information of the current time period in the current period; determine the historical road traffic information of the time period to be predicted in the historical period information; wherein, the time period to be predicted is after the current time period; according to the historical road traffic information and the real-time road traffic information of the current time period, and the historical road traffic information of the time period to be predicted, The real-time road condition information in the current cycle of at least two to-be-predicted moments in the to-be-predicted time period is predicted. The adoption of the above technical means can improve the accuracy of the road condition prediction, and satisfy the user's demand for the road condition prediction.

Description

Road condition prediction method, device, electronic device and storage medium

technical field

The present application relates to the field of computer technology, in particular to the field of intelligent transportation technology, and in particular to a road condition prediction method, device, electronic device and storage medium.

Background technique

With the continuous and rapid growth of car ownership in the country, the problem of urban road traffic congestion is becoming more and more serious, and people's attention and demand for road condition forecasting are also increasing.

Traffic managers are paying more and more attention to monitoring and forecasting traffic conditions for better traffic governance; ordinary users are paying more and more attention to forecasting future road conditions in order to make more reasonable travel plans.

SUMMARY OF THE INVENTION

The present application provides a road condition prediction method, device, electronic device and storage medium.

According to a first aspect of the present application, a road condition prediction method is provided, including:

Determine the historical road traffic information of the current time period in the historical period;

determining the real-time road traffic information of the current time period in the current cycle;

determining the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period;

According to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period, it is predicted that at least two to-be-predicted times in the to-be-predicted time period will be in the current Real-time traffic information in cycles.

According to a second aspect of the present application, a road condition prediction device is provided, comprising:

The historical road traffic information determination module of the current time period is used to determine the historical road traffic information of the current time period in the historical period;

The real-time road traffic information determination module of the current time period is used to determine the real-time road traffic information of the current time period in the current cycle;

A historical road traffic information determination module for the time period to be predicted, for determining the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period;

The real-time road condition information prediction module is used to predict at least two of the to-be-predicted time periods according to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period. The real-time road condition information of the time to be predicted in the current cycle.

According to a third aspect of the present application, an electronic device is provided, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any of the present application.

According to a fourth aspect of the present application, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method of any one of the present application.

The technology according to the present application can improve the accuracy of road condition prediction.

It should be understood that the content described in this section is not intended to identify key or critical features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the present application will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

FIG. 1 is a schematic flowchart of a road condition prediction method provided according to an embodiment of the present application;

2a is a schematic flowchart of another road condition prediction method provided according to an embodiment of the present application;

2b is a schematic diagram of a model framework of an LSTM provided according to an embodiment of the present application;

3 is a schematic flowchart of another road condition prediction method provided according to an embodiment of the present application;

4 is a schematic structural diagram of a road condition prediction device provided according to an embodiment of the present application;

FIG. 5 is a block diagram of an electronic device for a road condition prediction method provided according to an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

FIG. 1 is a schematic flowchart of a road condition prediction method provided according to an embodiment of the present application. This embodiment can be applied to a situation in which the road conditions of a road in a future period are predicted. The road condition prediction method disclosed in this embodiment may be executed by an electronic device, and specifically may be executed by a road condition prediction apparatus, which may be implemented by software and/or hardware and configured in the electronic device. Referring to FIG. 1 , the road condition prediction method provided in this embodiment includes:

S110. Determine the historical road traffic information in the historical period of the current time period.

In this embodiment, a single time period may include at least two time periods, and a single time period may include at least two road condition moments. The time period can be divided by days, weeks or other ways. In the case of dividing the time period by days, the current day is the current period, and the days before the current day can be historical periods. In the case of dividing the time period by weeks , the current week is the current cycle, and the weeks before the current week can be historical cycles. A single time period can be divided into at least two road condition prediction moments every fixed time period, for example, a time period of 1 hour can be divided into 12 road condition prediction moments every 5 minutes.

The current time period refers to the time period to which the current moment belongs, and the duration of the current time period may be a fixed value. The specific time interval between the start time of the current time period and the current time may be a fixed value, and the end time of the current time period may be the current time. Taking the current time as 10:15, the time period is divided by day, and the duration of the time period is 1 hour, for example, the current time period may be from 9:15 to 10:15.

The road traffic information in the historical road traffic information and the subsequent real-time road traffic information both refers to the road condition information of the road, and the road traffic information may include the speed and trajectory of the road to be predicted and the adjacent road. Specifically, the adjacent road is the upstream road of the road to be predicted or the downstream road of the road to be predicted, wherein the number of upstream roads may be M, and the number of downstream roads may be N, wherein M and N have different values. Exemplarily, the values of M and N are both greater than or equal to 3. The historical road traffic information of the current time period in the historical period refers to the historical road traffic information of the road under the current time period of the historical period. For example, in the time period from 9:15 to 10:15 before today, the Historical road traffic information. In this embodiment, the road traffic information includes not only the road condition information of the road to be predicted, but also the road condition information of the adjacent roads. Therefore, the relationship between the road to be predicted and the adjacent road can be used to better describe the influence of the spatial topological relationship on the road condition of the predicted road.

Specifically, the historical road traffic information of at least two road condition moments in the historical period of the current time period is acquired. For example, historical road traffic information of at least two road condition moments in the historical period from 9:15 to 10:15 may be acquired.

S120. Determine the real-time road traffic information of the current time period in the current cycle.

In this embodiment, the real-time road traffic information of the current time period in the current period refers to the real-time road traffic information of the road under the current time period of the current period, for example, in the time period from 9:15 to 10:15 today Below, the real-time road traffic information of the road.

S130. Determine the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period.

In this embodiment, the to-be-predicted time period refers to a time period after the current time period, and the length of the to-be-predicted time period is the same as the length of the current time period, and both may be fixed values. The start time of the to-be-predicted time period may be the current time, and the time interval between the end time of the to-be-predicted time period and the current time may be a fixed value. Exemplarily, the current time period refers to 9:15 to 10:15, and the to-be-predicted time period may be from 10:15 to 11:15. The historical road traffic information of the to-be-predicted time period in the historical period refers to the historical road traffic information of the road in the to-be-predicted time period of the historical period.

S140. According to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period, predict that at least two to-be-predicted times in the to-be-predicted time period will be The real-time road condition information in the current cycle is described.

In this embodiment, the to-be-predicted time period may include at least two road condition prediction moments, ie, to-be-predicted moments, for example, one to-be-predicted time may be taken every 5 minutes. Taking the time period to be predicted as 10:15 to 11:15 as an example, the time to be predicted can be 10:20, 10:25, ... 11:10 and 11:15, a total of 12 times.

In this embodiment, the current time period includes both historical road traffic information in the historical period and real-time road traffic information in the current period. By processing the historical road traffic information and the real-time road traffic information, it is possible to determine the current The road condition relationship between the period and the historical period, for example, the road conditions between the current period and the historical period are similar, or the road conditions are different. According to the road condition relationship between the current period and the historical period, and the historical road traffic information of the time period to be predicted in the historical period, the real-time road condition information of the time to be predicted in the time period to be predicted in the current period is determined. Since the real-time road condition information at the moment to be predicted is determined based on the road condition relationship between the current period and the historical period, the road conditions of the current period and the historical period are fully considered, and the historical law and real-time characteristics of the road can be combined to improve the time period to be forecasted. The road conditions of the time to be predicted in the current cycle are accurate, and since multiple different times to be predicted in the time period to be predicted can be predicted, the road condition information of the road to be predicted is more refined.

The technical solution of the embodiment of the present application is to determine the historical road traffic information of the current time period in the historical period; determine the real-time road traffic information of the current period of time in the current period; determine that the to-be-predicted time period is in the historical period According to the historical road traffic information of the current time period and the real-time road traffic information, and the history of the to-be-predicted time period Road traffic information, predicting real-time road condition information in the current cycle at at least two to-be-predicted time periods in the to-be-predicted time period. The adoption of the above technical means can improve the accuracy of the road condition prediction, and satisfy the user's demand for the road condition prediction.

Fig. 2a is a schematic flowchart of a road condition prediction method provided according to an embodiment of the present application. This embodiment is an optional solution proposed on the basis of the foregoing embodiment. Referring to Fig. 2a, the road condition prediction method provided in this embodiment includes:

S210. Determine the historical road traffic information in the historical period of the current time period.

S220. Determine the real-time road traffic information of the current time period in the current cycle.

S230. Determine the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period.

S240. Determine the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information.

In this embodiment, the historical weight of the time period to be predicted is used to measure the similarity of the road conditions of the time period to be predicted and the current time period. The higher the historical weight, the higher the similarity of the road conditions between the time period to be predicted and the current time period. Specifically, if the similarity between the historical road traffic information of the current time period and the real-time road traffic information is relatively high, the possibility of high similarity between the historical road traffic information of the to-be-predicted time period and the real-time road traffic information of the to-be-predicted time period will be high. larger. Therefore, correspondingly, the historical weight of the time period to be predicted will be relatively high.

In this embodiment, the historical weight can be dynamically calculated to measure the similarity between the current time period and the to-be-predicted time period.

Optionally, determining the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information, including:

According to the historical road traffic information of the current time period, determine the historical time series latent feature vector of the current time period;

According to the real-time road traffic information of the current time period, determine the real-time time series latent feature vector of the current time period;

The product between the historical time series latent feature vector of the current time period and the real-time time series latent feature vector is used as the historical weight of the to-be-predicted time period.

In this embodiment, the historical time series latent feature vector of the current time period is obtained by inputting the historical road traffic information of the current time period into an LSTM (Long-Short Term Memory, long short-term memory model). Among them, LSTM is a special RNN (Recurrent Neural Network, cyclic neural network) model, which is proposed to solve the problem of gradient dispersion of the RNN model; in the traditional RNN, the training algorithm uses BPTT (Back Propagation TroughTime, Time-based backpropagation), when the time is relatively long, the residual error that needs to be returned decreases exponentially, resulting in a slow update of the network weight, which cannot reflect the long-term memory effect of RNN, so a storage unit is needed to store the memory. Therefore, LSTM Been proposed. The real-time time series latent feature vector of the current time period is obtained by inputting the real-time road traffic information of the current time period into the LSTM. The historical weight of the time period to be predicted can be obtained by multiplying the historical time series latent feature vector of the current time period and the real-time time series latent feature vector.

Comparing the real-time traffic characteristics of the current time period with the historical traffic characteristics to obtain a similarity, the reference value of the historical characteristics can be introduced, so that the road condition prediction of the to-be-predicted time period is more accurate.

S250, predict at least two to-be-predicted moments in the to-be-predicted time-segment according to the real-time road traffic information of the current time-segment, the historical weight of the to-be-predicted time-segment, and the historical road-traffic information of the to-be-predicted time segment Real-time traffic information in the current period.

In this embodiment, according to the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period, it can be determined whether the real-time road condition information of the to-be-predicted time period in the current cycle can be determined according to the historical road traffic information of the to-be-predicted time period information to be determined. If the historical weight of the time period to be predicted is lower, the weight of the real-time road traffic information of the current time period is higher, that is, the similarity of the real-time road traffic information of the to-be-predicted time period and the current time period is higher.

Specifically, please refer to the schematic diagram of the model framework of an LSTM shown in FIG. 2b. Among them, it can be seen that a specific value can be determined by the historical time series latent feature vector of the current time period and the real-time time series latent feature vector, and used as the historical weight of the time period to be predicted. Then, the historical weight of the time period to be predicted and the historical road traffic information of the time period to be predicted are dimensionally combined through aggregation in the LSTM model, and output.

Optionally, according to the real-time road traffic information of the current time period, the historical weight of the to-be-predicted time period, and the historical road traffic information of the to-be-predicted time period, predict at least two of the to-be-predicted time periods. The real-time road condition information of the time to be predicted in the current cycle, including:

According to the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period, determine the historical correction feature of the to-be-predicted time period;

Aggregating the real-time road traffic information of the current time period and the historical correction features of the to-be-predicted time period to obtain aggregated road features;

Semantic encoding is performed on the aggregated road features to obtain real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle.

In this embodiment, the historical correction feature of the time period to be predicted is used as an indicator of historical road traffic conditions of the time period to be predicted, and the historical correction feature of the time period to be predicted can more accurately reflect the historical law of the time period to be predicted. Aggregated road features refer to comprehensive features that combine the features of real-time road traffic information in the current time period and the historical correction features of the time period to be predicted. Use aggregated road features to determine real-time road conditions for the time period to be predicted.

In this embodiment, by using real-time features and historical features, changes in traffic laws can be better depicted dynamically.

The technical solution of the embodiment of the present application determines the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information, and then determines the historical weight of the to-be-predicted time period according to the real-time road traffic information of the current time period information, the historical weight of the to-be-predicted time period, and the historical road traffic information of the to-be-predicted time period, to predict the real-time road condition information of at least two to-be-predicted moments in the to-be-predicted time period in the current cycle. By using the above technical means, real-time features and historical laws can be used at the same time, and changes in traffic laws can be better depicted dynamically, which can not only reflect changes in road conditions caused by changes in real-time traffic environments, but also reflect the periodic laws of historical road conditions.

FIG. 3 is a schematic flowchart of a road condition prediction method provided according to an embodiment of the present application. This embodiment is an optional solution proposed on the basis of the foregoing embodiment. Referring to FIG. 3 , the road condition prediction method provided in this embodiment includes:

S310. Determine the historical road traffic information in the historical period of the current time period.

S320. Determine the real-time road traffic information of the current time period in the current cycle.

S330. Determine the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period.

S340. Determine the static attribute information of the road to be predicted.

In this embodiment, the static attribute information of the road to be predicted includes the road level and/or the number of lanes of the road to be predicted. Among them, the road level is to segment the road to be predicted, and each segment is a different level. Exemplarily, the road class may be class 1, class 2, up to class N. After taking the static attribute information of the road to be predicted as a reference value, the static attributes of the road to be predicted can be synthesized, thereby making the analyzed data more comprehensive and further improving the accuracy of road condition prediction.

S350. According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the static attribute information of the to-be-predicted road, predict the to-be-predicted time The real-time road condition information of at least two to-be-predicted moments in the segment in the current cycle.

In this embodiment, the static attribute information of the road to be predicted is introduced, which can better describe the influence of the road condition of the road to be predicted by the spatial topological relationship.

Optionally, according to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period, predict at least two to-be-predicted time periods in the to-be-predicted time period. The real-time road condition information in the current cycle at the predicted time, including:

According to the navigation request data, predict the traffic flow of the road to be predicted at at least two to-be-predicted moments in the to-be-predicted time period;

According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period Traffic flow, and predict the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle.

In this embodiment, the navigation request data refers to a navigation request message sent by a navigation search engine. The traffic flow of the road to be predicted at at least two times to be predicted in the time period to be predicted can be acquired. Among them, the data of traffic flow is relatively accurate, but relatively sparse. In this embodiment, by introducing the data information of the traffic flow, the accuracy of the road condition prediction can be further improved.

Optionally, according to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period, predict at least two to-be-predicted time periods in the to-be-predicted time period. The real-time road condition information in the current cycle at the predicted time, including:

According to the positioning data of the user equipment, predict the vehicle density of the road to be predicted at at least two to-be-predicted moments in the to-be-predicted time period;

According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period The vehicle density is used to predict the real-time road condition information of at least two to-be-predicted moments in the to-be-predicted time period in the current cycle.

In this embodiment, the user equipment may be a smart phone, a tablet, or a notebook computer that is carried by the user. After the user equipment is connected to the network, the vehicle is positioned according to the built-in positioning of the user equipment to obtain vehicle densities of at least two roads to be predicted in the to-be-predicted time period. In this embodiment, by introducing data information of vehicle density, the accuracy of road condition prediction can be further improved by analyzing vehicle conditions on the road to be predicted.

FIG. 4 is a schematic structural diagram of a road condition prediction apparatus provided by an embodiment of the present application, and the apparatus may be configured in an electronic device. Referring to FIG. 4 , the road condition prediction apparatus 400 provided in this embodiment of the present application may include:

The historical road traffic information determination module 410 of the current time period is used to determine the historical road traffic information of the current time period in the historical period;

The real-time road traffic information determination module 420 of the current time period is configured to determine the real-time road traffic information of the current time period in the current cycle;

The historical road traffic information determination module 430 of the time period to be predicted is configured to determine the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period;

The real-time road condition information prediction module 440 is configured to predict, according to the historical road traffic information and the real-time road traffic information of the current time period, and the historical road traffic information of the to-be-predicted time period, at least one of the to-be-predicted time periods. The real-time road condition information of the two to-be-predicted times in the current cycle.

Optionally, the real-time road condition information prediction module 440 includes:

a historical weight determination submodule, configured to determine the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information;

The real-time road condition information prediction submodule is used to predict the to-be-predicted time period according to the real-time road traffic information of the current time period, the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period The real-time road condition information of at least two to-be-predicted moments in the current cycle.

Optionally, the historical weight determination submodule is configured to determine the historical time series latent feature vector of the current time period according to the historical road traffic information of the current time period;

According to the real-time road traffic information of the current time period, determine the real-time time series latent feature vector of the current time period;

The product between the historical time series latent feature vector of the current time period and the real-time time series latent feature vector is used as the historical weight of the to-be-predicted time period.

Optionally, the real-time road condition information prediction sub-module is configured to determine the historical correction feature of the to-be-predicted time period according to the historical weight of the to-be-predicted time-segment and the historical road traffic information of the to-be-predicted time period;

Aggregating the real-time road traffic information of the current time period and the historical correction features of the to-be-predicted time period to obtain aggregated road features;

Semantic encoding is performed on the aggregated road features to obtain real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle.

Optionally, the historical road traffic information includes the historical speed and historical trajectory of the road to be predicted and the adjacent road; the real-time road traffic information includes the real-time speed and real-time trajectory of the road to be predicted and the adjacent road.

Optionally, the real-time road condition information prediction module 440 is configured to determine the static attribute information of the road to be predicted;

According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the static attribute information of the to-be-predicted road, it is predicted that the Real-time road condition information of at least two times to be predicted in the current cycle.

Optionally, the static attribute information of the road to be predicted includes a road level and/or the number of lanes of the road to be predicted.

Optionally, the real-time road condition information prediction module 440 is configured to predict the traffic flow of the road to be predicted at at least two to-be-predicted times in the to-be-predicted time period according to the navigation request data;

According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period Traffic flow, and predict the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle.

Optionally, the real-time road condition information prediction module 440 is configured to predict the vehicle density of the road to be predicted at at least two to-be-predicted moments in the to-be-predicted time period according to the positioning data of the user equipment;

According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period The vehicle density is used to predict the real-time road condition information of at least two to-be-predicted moments in the to-be-predicted time period in the current cycle.

The technical solution of the embodiment of the present application is to determine the historical road traffic information of the current time period in the historical period; determine the real-time road traffic information of the current period of time in the current period; determine that the to-be-predicted time period is in the historical period According to the historical road traffic information of the current time period and the real-time road traffic information, and the history of the to-be-predicted time period Road traffic information, predicting real-time road condition information in the current cycle at at least two to-be-predicted time periods in the to-be-predicted time period. The adoption of the above technical means can improve the accuracy of the road condition prediction, and satisfy the user's demand for the road condition prediction.

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 5 , it is a block diagram of an electronic device according to a road condition prediction method according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 5, the electronic device includes: one or more processors 501, a memory 502, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, each providing some of the necessary operations (eg, as a server array, a group of blade servers, or a multiprocessor system). A processor 501 is taken as an example in FIG. 5 .

The memory 502 is the non-transitory computer-readable storage medium provided by the present application. Wherein, the memory stores instructions executable by at least one processor, so that the at least one processor executes the road condition prediction method provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the road condition prediction method provided by the present application.

As a non-transitory computer-readable storage medium, the memory 502 can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the road condition prediction method in the embodiments of the present application (for example, appendix). The historical road traffic information determination module 410 of the current time period, the real-time road traffic information determination module 420 of the current time period, the historical road traffic information determination module 430 of the to-be-predicted time period, and the real-time road condition information prediction module 440 shown in FIG. 4 . The processor 501 executes various functional applications of the server and road condition prediction by running the non-transitory software programs, instructions and modules stored in the memory 502, ie, implements the road condition prediction method in the above method embodiments.

The memory 502 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the electronic device displayed by the point of interest, etc. . Additionally, memory 502 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 502 may optionally include memory located remotely from the processor 501, and these remote memories may be connected via a network to the electronic device displaying the point of interest. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device of the road condition prediction method may further include: an input device 503 and an output device 504 . The processor 501 , the memory 502 , the input device 503 and the output device 504 may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 5 .

The input device 503 can receive input numerical or character information, and generate key signal input related to user settings and function control of the electronic device displaying the point of interest, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick, One or more input devices such as mouse buttons, trackballs, joysticks, etc. The output device 504 may include a display device, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

The technical solution of the embodiment of the present application is to determine the historical road traffic information of the current time period in the historical period; determine the real-time road traffic information of the current period of time in the current period; determine that the to-be-predicted time period is in the historical period According to the historical road traffic information of the current time period and the real-time road traffic information, and the history of the to-be-predicted time period Road traffic information, predicting real-time road condition information in the current cycle at at least two to-be-predicted time periods in the to-be-predicted time period. The adoption of the above technical means can improve the accuracy of the road condition prediction, and satisfy the user's demand for the road condition prediction.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (20)

1. A road condition prediction method, comprising: Determine the historical road traffic information of the current time period in the historical period; determining the real-time road traffic information of the current time period in the current cycle; determining the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period; According to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period, it is predicted that at least two to-be-predicted times in the to-be-predicted time period will be in the current Real-time traffic information in cycles. 2. The method according to claim 1, wherein said predicting said The real-time road condition information of at least two to-be-predicted moments in the current cycle in the to-be-predicted time period, including: determining the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information; According to the real-time road traffic information of the current time period, the historical weight of the to-be-predicted time period, and the historical road traffic information of the to-be-predicted time period, it is predicted that at least two of the to-be-predicted time periods in the to-be-predicted time period will be in the The real-time road condition information in the current cycle is described. 3. The method according to claim 2, wherein, determining the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information, comprising: According to the historical road traffic information of the current time period, determine the historical time series latent feature vector of the current time period; According to the real-time road traffic information of the current time period, determine the real-time time series latent feature vector of the current time period; The product between the historical time series latent feature vector of the current time period and the real-time time series latent feature vector is used as the historical weight of the to-be-predicted time period. 4. The method according to claim 2, wherein, according to the real-time road traffic information of the current time period, the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period, predicting The real-time road condition information of at least two to-be-predicted moments in the current cycle in the to-be-predicted time period, including: According to the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period, determine the historical correction feature of the to-be-predicted time period; Aggregating the real-time road traffic information of the current time period and the historical correction features of the to-be-predicted time period to obtain aggregated road features; Semantic encoding is performed on the aggregated road features to obtain real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle. 5. The method according to any one of claims 1-4, wherein the historical road traffic information includes the historical speed and historical trajectory of the road to be predicted and adjacent roads; the real-time road traffic information includes the road to be predicted and real-time speed and real-time trajectory of adjacent roads. 6. The method according to any one of claims 1-4, wherein the historical road traffic information according to the current time period and the real-time road traffic information, and the historical road of the to-be-predicted time period Traffic information, predicting the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle, including: Determine the static attribute information of the road to be predicted; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the static attribute information of the to-be-predicted road, it is predicted that the Real-time road condition information of at least two times to be predicted in the current cycle. 7. The method according to claim 6, wherein the static attribute information of the road to be predicted includes a road level and/or the number of lanes of the road to be predicted. 8. The method according to any one of claims 1-4, wherein the historical road traffic information according to the current time period and the real-time road traffic information, and the historical road of the to-be-predicted time period Traffic information, predicting the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle, including: According to the navigation request data, predict the traffic flow of the road to be predicted at at least two to-be-predicted moments in the to-be-predicted time period; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period Traffic flow, and predict the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle. 9. The method according to any one of claims 1-4, wherein the historical road traffic information according to the current time period and the real-time road traffic information, and the historical road of the to-be-predicted time period Traffic information, predicting the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle, including: According to the positioning data of the user equipment, predict the vehicle density of the road to be predicted at at least two to-be-predicted moments in the to-be-predicted time period; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period The vehicle density is used to predict the real-time road condition information of at least two to-be-predicted moments in the to-be-predicted time period in the current cycle. 10. A road condition prediction device, comprising: The historical road traffic information determination module of the current time period is used to determine the historical road traffic information of the current time period in the historical period; The real-time road traffic information determination module of the current time period is used to determine the real-time road traffic information of the current time period in the current cycle; A historical road traffic information determination module for the time period to be predicted, for determining the historical road traffic information of the time period to be predicted in the historical period; wherein the time period to be predicted is after the current time period; The real-time road condition information prediction module is used to predict at least two of the to-be-predicted time periods according to the historical road traffic information of the current time period and the real-time road traffic information, and the historical road traffic information of the to-be-predicted time period. The real-time road condition information of the time to be predicted in the current cycle. 11. The device according to claim 10, wherein the real-time road condition information prediction module comprises: a historical weight determination submodule, configured to determine the historical weight of the to-be-predicted time period according to the historical road traffic information of the current time period and the real-time road traffic information; The real-time road condition information prediction submodule is used to predict the to-be-predicted time period according to the real-time road traffic information of the current time period, the historical weight of the to-be-predicted time-segment and the historical road traffic information of the to-be-predicted time period The real-time road condition information of at least two to-be-predicted moments in the current cycle. 12. The apparatus according to claim 11, wherein the historical weight determination submodule is used to determine the historical time series latent feature vector of the current time period according to the historical road traffic information of the current time period; According to the real-time road traffic information of the current time period, determine the real-time time series latent feature vector of the current time period; The product between the historical time series latent feature vector of the current time period and the real-time time series latent feature vector is used as the historical weight of the to-be-predicted time period. 13. The device according to claim 11, wherein the real-time road condition information prediction submodule is used to determine the to-be-predicted time period according to the historical weight of the to-be-predicted time period and the historical road traffic information of the to-be-predicted time period historical correction characteristics of the time period; Aggregating the real-time road traffic information of the current time period and the historical correction features of the to-be-predicted time period to obtain aggregated road features; Semantic encoding is performed on the aggregated road features to obtain real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle. 14. The apparatus according to any one of claims 10-13, wherein the historical road traffic information includes historical speeds and historical trajectories of the road to be predicted and adjacent roads; the real-time road traffic information includes the road to be predicted and real-time speed and real-time trajectory of adjacent roads. 15. The device according to any one of claims 10-13, wherein the real-time road condition information prediction module is used to determine static attribute information of a road to be predicted; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the static attribute information of the to-be-predicted road, it is predicted that the Real-time road condition information of at least two times to be predicted in the current cycle. 16. The apparatus according to claim 15, wherein the static attribute information of the road to be predicted comprises a road level and/or the number of lanes of the road to be predicted. 17. The device according to any one of claims 10-13, wherein the real-time road condition information prediction module is configured to predict the to-be-predicted at least two to-be-predicted moments in the to-be-predicted time period according to the navigation request data traffic flow on the road; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period Traffic flow, and predict the real-time road condition information of at least two to-be-predicted times in the to-be-predicted time period in the current cycle. 18. The apparatus according to any one of claims 10-13, wherein the real-time road condition information prediction module is configured to predict, according to the positioning data of the user equipment, the to-be-predicted times of at least two to-be-predicted time periods in the to-be-predicted time period. predicting the density of vehicles on the road; According to the historical road traffic information of the current time period and the real-time road traffic information, the historical road traffic information of the to-be-predicted time period, and the to-be-predicted roads of at least two to-be-predicted times in the to-be-predicted time period The vehicle density is used to predict the real-time road condition information of at least two to-be-predicted moments in the to-be-predicted time period in the current cycle. 19. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-9 Methods. 20. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method of any of claims 1-9.

Images