CN103177562B - A kind of method and device obtaining information of traffic condition prediction - Google Patents

Abstract

The present invention provides a method and device for obtaining information required for traffic state prediction to solve the problem existing in the prior art that a dedicated monitoring device is required to complete the collection of traffic state information. The method includes: the server obtains each The cell identification code CELLID of the cell, and the location information of each cell, according to the obtained cell ID cell identification code, obtain the identification information of the terminal under each cell from the network element storing the location information in the mobile network, and obtain the identification information with the read According to the last registration time of each terminal in each network element of the information, the information required for traffic state prediction can be obtained according to the location information of each cell and the last registration time of each terminal in each network element. Since the location information stored in the wireless network The relevant data is read from the network elements of the network, and the information required for traffic state prediction is obtained, so that the collection of traffic state information does not need a dedicated monitoring device.

Description

A method and device for obtaining information required for traffic state prediction

technical field

The invention relates to the field of mobile communication, in particular to a method and device for acquiring information required for traffic state prediction.

Background technique

The existing road traffic forecasting network is mainly established through questionnaires at designated intersections, manually collecting static prediction data on regional population flows, and obtaining current traffic information at designated intersections by arranging geographic sensing detection, video detection and other equipment at specific intersections. Real-time data. Then, through the two kinds of data, the traffic flow, traffic speed, travel time, etc. are predicted by the method of mathematical statistics. Geo-sensing technology, video detection technology and other technologies for road sections can only detect regional and specific road sections equipped with the above detection devices, and the cost is high, so it is difficult to popularize all road sections. It can be seen that when predicting the traffic state, it is often necessary to establish multiple monitoring points, and complete the collection of traffic state information such as vehicle speed and number of vehicles based on the monitoring points.

It can be seen that the following problems exist in the prior art: a dedicated monitoring device is required to complete the collection of traffic state information.

Contents of the invention

The purpose of the present invention is aimed at existing in the prior art, needs the problem that special-purpose monitoring device completes the collection of traffic state information, provides a kind of method and device for obtaining the required information of traffic state prediction, and this method comprises:

The server acquires the cell identification codes of each cell in the area to be predicted, and the location information of each cell;

According to the obtained cell identification code, the server obtains the identification information of the terminals in each cell from the network elements storing the location information in the mobile network, and obtains the last registration time of each terminal with the read identification information in each network element respectively;

The server obtains information required for traffic state prediction according to the location information of each cell and the last registration time of each terminal in each network element.

Further, the information required for traffic state prediction includes: the moving speed of the terminal within a predetermined period of time.

Further, the information required for traffic state prediction also includes: the moving path of the terminal within a predetermined time period.

Further, the information required for traffic state prediction includes: the server determines the type of vehicle that the terminal belongs to during the predetermined time period according to the moving speed of the terminal during the predetermined time period and the moving path of the terminal during the predetermined time period.

Further, it also includes:

Before predicting the traffic status, the server determines and stores the vehicle to which the terminal belongs, the vehicle to which The corresponding relationship between the driving path and the road occupancy rate, wherein the corresponding relationship between the road occupancy rate is the corresponding relationship between the road occupancy rate and the parameters used to represent the traffic state prediction results;

The server obtains the real-time road traffic status information on the roads in the area to be predicted during the scheduled time period of the traffic status prediction day;

According to the stored vehicle to which the terminal belongs and the driving path of the vehicle, the server obtains the number of vehicles that will enter and exit the road in the area to be predicted;

The server predicts the road occupancy rate according to the real-time road traffic state information and the number of vehicles entering and leaving, and predicts the traffic state according to the predicted road occupancy rate and the corresponding relationship of the stored road occupancy rate, and obtains the prediction result.

Further, the parameter representing the traffic state prediction result is the road transit time of the vehicle;

The server obtains the real-time road traffic state information on the roads in the area to be predicted for the predetermined time period of the day when the traffic state prediction is performed:

According to the total number of terminals on the roads in the area to be predicted during the scheduled time period of the day when the traffic status is predicted, the moving speed, moving path and vehicle type of each terminal, the server obtains the number of terminals on the roads in the area to be predicted during the scheduled time period of the forecasted day. The number of real-time vehicles N;

The server predicts the road occupancy rate based on the real-time road traffic status information, the number of vehicles entering and leaving, and predicts the traffic state according to the predicted road occupancy rate and the corresponding relationship between the stored road occupancy rate, and the prediction result is specifically: :

The server calculates the predicted road occupancy rate Pi, where Pi=Ni/C, Ni=N+In+Out, C is the design traffic volume, In is the number of vehicles that will enter the road in the area to be predicted, and Out is the road in the area to be predicted the number of vehicles to be driven out;

The server predicts the traffic state according to the predicted road occupancy rate Pi and the corresponding relationship between the road occupancy rate and the road passing time, and obtains the predicted road passing time.

Further, it also includes:

According to the navigation request including the destination address reported by the terminal, the server reads the location information of the cell to which the terminal belongs from the network element storing the location information in the mobile network;

The server selects a navigation route for the terminal according to the location information of the cell to which the terminal belongs, the destination address, and the predicted road passing time.

Further, the server selects a navigation path for the terminal according to the location information and destination address of the cell to which the terminal belongs, and the predicted road passing time, specifically:

The server determines the time-varying shortest path according to the location information and destination address of the cell to which the terminal belongs, and the predicted road passing time, and takes the time-varying shortest path as the navigation path selected for the terminal.

The embodiment of the present invention also provides a device for obtaining information required for traffic state prediction, including:

Position acquisition module: used to acquire the cell identification codes of each cell in the area to be predicted, and the location information of each cell;

Time acquisition module: used to obtain the identification information of the terminals in each cell from the network elements that store location information in the mobile network according to the acquired cell identification code, and obtain the identification information of each terminal with the read identification information in each network element Last registration time;

Information acquisition module: used to obtain the information required for traffic state prediction according to the location information of each cell and the last registration time of each terminal in each network element.

Further, it also includes:

Storage module: used to determine and store in the predetermined time period, the vehicle to which the terminal belongs according to the number of terminals, terminal moving speed, terminal moving path and the type of vehicle to which the terminal belongs within a predetermined number of days before predicting the traffic state. , the corresponding relationship between the driving path of the vehicle and the road occupancy rate, wherein the corresponding relationship between the road occupancy rate is the corresponding relationship between the road occupancy rate and the parameters used to represent the traffic state prediction results, and the information required for the traffic state prediction includes: The moving speed of the predetermined time period, the moving path of the terminal in the predetermined time period, and the vehicle type determined according to the moving speed of the terminal in the predetermined time period and the moving path of the terminal in the predetermined time period.

Real-time acquisition module: used to obtain real-time road traffic status information on the roads in the area to be predicted during the scheduled time period of the traffic status prediction day;

Quantity determination module: used to obtain the number of vehicles that will enter and leave the road in the area to be predicted according to the stored vehicle to which the terminal belongs and the driving path of the vehicle;

Result prediction module: it is used to predict the road occupancy rate according to the real-time road traffic state information, the number of vehicles entering and leaving, and predict the traffic state according to the predicted road occupancy rate and the corresponding relationship of the stored road occupancy rate, and obtain forecast result.

Further, the parameter representing the traffic state prediction result is the road transit time of the vehicle;

Real-time acquisition module: it is also used to predict the scheduled time period of the day according to the traffic status prediction, the total number of terminals on the road in the area to be predicted, the moving speed, moving path and vehicle type of each terminal, and obtain the scheduled time period of the forecasted day, The number of real-time vehicles N on the road in the area to be predicted;

Result prediction module: it is also used to calculate the predicted road occupancy rate Pi, wherein Pi=Ni/C, C is the design traffic volume, Ni=N+In+Out, In is the quantity that will enter the vehicle on the road to be predicted area, Out is the number of vehicles that will drive out on the road in the area to be predicted;

The server predicts the traffic state according to the predicted road occupancy rate Pi and the corresponding relationship between the road occupancy rate and the road passing time, and obtains the predicted road passing time.

Further, it also includes:

Reading module: used to read the location information of the cell to which the terminal belongs from the network element storing the location information in the mobile network according to the navigation request including the destination address reported by the terminal;

Selection module: used to select a navigation route for the terminal according to the location information and destination address of the cell to which the terminal belongs, as well as the predicted road passing time.

Further, the selection module: it is also used to determine the shortest path with time variation according to the location information and destination address of the cell to which the terminal belongs, and the predicted road transit time, and use the shortest path with time variation as the navigation path selected for the terminal.

Since the relevant data is read from the network element storing the location information in the mobile network, the information required for the traffic state prediction is obtained, and the collection of the traffic state information does not need a dedicated monitoring device.

Description of drawings

Fig. 1 represents the system architecture diagram that adopts when the concrete implementation that the present invention provides;

Fig. 2 represents the method flowchart provided by the present invention;

Fig. 3 represents the traffic prediction network node schematic diagram provided by the present invention;

Fig. 4 represents the schematic diagram of the required traffic prediction network nodes for the shortest path calculation provided by the present invention;

Fig. 5 shows the structural diagram of the device provided by the present invention.

Detailed ways

The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. The embodiments of the present invention provide a method and device for obtaining information required for traffic state prediction to solve the problem in the prior art that a dedicated monitoring device is required to complete the traffic state information. collection problem.

In this embodiment, the server obtains the cell identification codes of each cell in the area to be predicted, and the location information of each cell, and the server obtains the location information from the network element in the mobile network such as the visitor location register of the mobile network according to the obtained cell identification code. Read in the VLR, the identification information of the terminal in each cell, and the last registration time of the terminal in each network element respectively, and the server obtains Information required for traffic state prediction. The network element storing the location information in the mobile network may also be MSC (Mobile Switching Center), Softswitch Controller, SGSN, MME, HSS, etc.

In the actual implementation of this embodiment, the navigation system based on the intelligent traffic prediction network is installed in the server, which can realize the acquisition of the information required for traffic state prediction and navigation services, and the functional modules included in the system architecture that it adopts are as follows: map database 101 , VLR reading module 102, VLR data analysis module 103, historical data storage module 104, traffic state prediction module 105, personal navigation module 106.

The map database 101 performs information interaction with the traffic state prediction module 105 and the VLR reading module 102, and includes road information and cell information distributed around the road. The map information of the main package road, and each road contains the geographic location information corresponding to the cell ID CELLID of the community, and the information of each road to which it belongs (including the lane number N of the road, whether it is a one-way street, etc.); provide the corresponding traffic state prediction module Static map information data; provide the CELLID information to be read to the VLR reading module.

The VLR reading module 102 performs information interaction with the map database 101, the VLR data analysis module 103 and the VLR, and is a module entity for reading real-time location information from the VLR. Mainly responsible for: obtaining cell ID information to be read from the map database; obtaining relevant MS information of each cell ID from the VLR according to the read cell ID information, such as IMSI, last registration time and other data; integrating the above information, Provide corresponding data to the VLR data analysis module.

The VLR data analysis module 103 performs information interaction with the VLR reading module 102 , the historical data storage module 104 and the traffic state prediction module 105 . It is mainly responsible for two functions: analysis and processing of real-time data, analysis of terminal operating status, and submitting the current status of the terminal to the traffic status prediction module; analyzing real-time data within a period of time, analyzing and judging the historical path of each terminal , saving the path information to the historical data storage module.

The historical data storage module 104 may be a real-time updated data storage module. Information interaction with VLR data analysis module and traffic state prediction module. Receive the message from the VLR data analysis module, analyze and save the main type (bus, private car) of each terminal in public transportation, and the common route information of each terminal at different time periods. At the same time, it provides the historical information of the terminal to the traffic state prediction module.

The traffic state prediction module 105 carries out information interaction with the map database 101, the VLR data analysis module 103, the historical data storage module 104, and the personal navigation module 106, based on the map information from the map database, the historical path information from the historical data storage module and the The real-time information of the current road condition in the VLR data analysis module predicts the traffic state. Mainly responsible: From the static data such as geographic location information corresponding to the cell ID CELLID in the map database, the number of lanes, etc.; through the real-time data from the VLR data analysis module, analyze and obtain the number of vehicles driving on the current road, the direction of the vehicle, and the number of vehicles. Average driving speed, road occupancy rate and other data; obtain the path of the vehicle driving on the current road from the historical data storage module, and predict the vehicle leaving the current road. Combining the information of the three, the traffic status of each road in the next time period can be predicted.

The personal navigation module 106 performs information interaction with the traffic state prediction module 105 and the VLR analysis module 103 . For a specific user, the personal navigation module selects a reasonable route for the user according to the user's location information in the VLR analysis module, the destination information set by the user, and the traffic status predicted by the traffic prediction module.

Of course, the division of the above functional modules is just to facilitate the implementation of the solution of this embodiment, and this embodiment does not limit it.

Based on the above-mentioned system architecture, the flow chart of the method provided by the embodiment of the present invention is shown in Figure 2 below, including the following steps:

Step 201. Initialization: the system connects to the mobile network and imports the static map data from the map database into the traffic state prediction module. The static map data includes: the location information of the base station cell in the map, the cell range information, the number of road lanes and other static data.

Through this step, the server can obtain the location information of each cell in the area to be predicted.

Step 202. Acquisition of location information data: the VLR reading module reads the CELLID from the map database, and according to the read CELLID information, obtains relevant information of the mobile terminal MS subordinate to each CELLID from the VLR, such as IMSI, and the last registration time and other data.

Since the state of the road is detected, it is only necessary to pay attention to the location information of the mobile terminal near the road, that is, the area to be predicted. According to the map database, the cell IDs of the cells distributed near the road are needed for the road information. Therefore, further Only read user information near roads, including, IMSI, last login time, etc. Here, the terminals registered in each cell can be obtained, and the last registration time of the cell is obtained.

Through this step, the server can obtain the cell identification code CELLID of each cell in the area to be predicted, and, according to the obtained CELLID, read the identification information of the terminal under each cell from the VLR, such as IMSI, and register each terminal at the end of each network element respectively time.

Step 203. VLR data analysis: the VLR data analysis module reads data from the VLR reading module, and performs the following operations according to the data from the VLR reading module: terminal moving speed calculation, terminal moving path calculation, and terminal vehicle type judgment .

The mobile terminal will perform location update in the following situations: normal location update (that is, location update beyond the location area), periodic location update and IMSI attachment and detachment (corresponding to user power-on), and service initiation. According to the modification of the VLR data when the mobile terminal position is updated, the data therein can be analyzed.

The operation of the VLR data analysis module will be described in detail below.

Terminal moving speed calculation: according to the cell ID corresponding to the terminal IMSI in the VLR, and the last login time, you can get the location of the terminal at the last moment; the distance corresponding to the cell information on the map corresponding to the two location updates is divided by two times The time interval for updating the location is the moving speed of the terminal.

Movement path calculation: According to the updated cell information of the terminal location, record the path of the terminal at different times. The location from the last location update to the next location update is the moving direction of the terminal.

Analysis of the types of vehicles that the terminal belongs to: the main types of vehicles on the highway are: buses, taxis, private cars, and pedestrians. When predicting traffic conditions, it is necessary to distinguish the means of transport used by the terminal at different times.

Judgment on pedestrians: According to the calculated moving speed of the terminal, within a certain period of time, a terminal that maintains low-speed movement for a long time and has an irregular action path is judged to be a normal walking mode during this period of time. Specifically, it is low-speed movement or High-speed movement can be judged by comparing with a set threshold, for example, the threshold is set to 10 km/h.

Judgment on the bus: According to the calculated moving speed and moving path of the terminal, according to the particularity of the bus driving, it can be judged that the means of transportation of the terminals that move on the designated path most of the day are bus drivers terminal held. At the same time, most of the time is still, and within a certain period of time, the terminal that matches the driving path and terminal state of the bus driver's terminal is judged. During this time period, the vehicle used is a bus.

Judgment on the taxi: According to the calculated moving speed and moving path of the terminal, since the behavior of the taxi is to move at high speed on the road for a long time, and the moving path is uncertain, it can be judged that the vehicle where the terminal is located is a taxi. Within a specific time period, the terminal whose moving speed and moving path are consistent with the taxi is determined to be a taxi to which the terminal belongs within this time period.

For the judgment of private cars, according to the calculated moving speed and moving path of the terminal, the terminal that does not move at high speed on the road for a long time within a day, and the starting point and end point of the movement are similar, can be judged as the vehicle to which the terminal belongs for a private car.

Through the example description of the analysis method for the type of vehicle to which the terminal belongs, it can be seen that the server can determine that the type of vehicle that the terminal belongs to in the predetermined time period is bus car, taxi or private car.

Step 204. Acquisition of historical data: According to the path information from the VLR data analysis module, through a long period of processing, the most frequently passed path of the terminal can be obtained as the historical path of a certain period of time. When the time threshold is reached, the road state prediction module is informed to start working, and the historical data is sent to the road state prediction module.

According to the information of the VLR data analysis module, the number of terminals, the moving speed of each terminal, the moving path, and the type of vehicle in different time periods are synthesized. In a longer time range such as one month, each The vehicle to which the terminal belongs in different time periods and the driving route of the vehicle are saved. Use this information as an estimate of the maximum possible behavior of this terminal's traffic engagement over different time periods. For example, there are a total of 100 terminals, 30 of which have the same moving speed and the same moving path, and the type of vehicle they belong to is a bus. It is determined that the vehicles to which these 30 terminals belong are the same bus, and the other 70 terminals can be judged similarly. What are the means of transport to which the terminal belongs?

In this way, the server can predict the traffic status according to the number of terminals, the moving speed, the moving path during the predetermined time period, and the vehicle to which it belongs during the predetermined time period for a certain number of days, such as a predetermined time period within a month, such as 8:00 am to 9:00 am. Type, determine and store within a predetermined period of time, the vehicle to which the terminal belongs, and the driving route of the vehicle.

According to the information of the VLR data analysis module, the road occupancy rate and the average driving speed of vehicles in the road occupancy rate at different times are mapped one by one, and the corresponding average driving speed of the road at different occupancy rates is obtained as the average driving speed on the road at different times estimated value. In the case of different road occupancy rates, the average passing time obtained by dividing the road length by the average driving speed is stored as the corresponding passing time at the current road occupancy rate. The number of terminals, the moving speed of each terminal, the moving path, and the type of vehicle to which it belongs can obtain the number of vehicles on the road, for example, a total of 100 terminals, and determine that the vehicles to which these 30 terminals belong are the same bus, and the other 70 The vehicles belonging to each terminal are 70 private cars respectively, then the real-time traffic flow, that is, the number of vehicles on the road N is 71, the road occupancy rate P=N/C, and C is the design traffic volume, which is a road factor and is influenced by the road Width, traffic lights and other effects. The average driving speed of the vehicle can be obtained according to the moving speed of each terminal and the condition of the vehicle to which each terminal belongs. Finally, the mapping between the road occupancy rate and the average driving speed of vehicles in the road occupancy rate at different times is obtained.

In this way, the server determines and stores the road occupancy in the predetermined time period according to the number of terminals, moving speed, moving path in the predetermined time period, and the type of vehicle in the predetermined time period during the predetermined time period within the predetermined number of days before the traffic state prediction. The road occupancy rate correspondence relationship is the correspondence relationship between the road occupancy rate and the parameters used to represent the traffic state prediction results (such as the average driving speed of the vehicle and the road transit time). Save the corresponding relationship of road occupancy rate as historical data for traffic forecasting.

When the historical data storage module completes the analysis and storage from the VLR data analysis module, the data of the historical data storage module is available.

The historical data storage module sends a ready command to the traffic state prediction module, notifies the traffic state prediction module to start working, and starts to send the stored historical data to the traffic state prediction module.

Step 205. Highway state prediction: when the traffic state prediction module receives the message that the historical data storage module is ready, it starts the traffic state prediction.

Traffic prediction start: the traffic state prediction module receives the ready information of the historical data storage module, reads the map database, and the real-time traffic information obtained by the analysis of the VLR data analysis module and the historical information of the historical data storage module.

Road traffic status reading: read the static information of the road from the map database module: the number of road lanes, geographical location, etc.; read the real-time road traffic status information of terminals on each road from the VLR data analysis module, such as the number of vehicles on the road N , the type of vehicles on the road, the road occupancy rate, the current average speed of the road, etc. In this way, the server can obtain the real-time road traffic status information on the roads in the area to be predicted for the predetermined time period of the traffic status prediction day

From the historical data storage module, the vehicles to which different terminals belong at this moment and their historical paths are obtained. Calculate the number of vehicles entering and exiting the road at the next moment respectively. For example, according to the historical path, there will be 20 vehicles (90 terminals belonging to these 20 vehicles) whose historical path is from Road No. 1 to Road No. 2, and there will be 10 vehicles (30 terminals belonging to these 10 vehicles respectively). )'s historical path is from No. 2 Road to No. 3 Road, then for No. 2 Road at the next moment, the number of vehicles entering is 20, and the number of vehicles leaving. The total number of vehicles on the road is 10. According to the real-time road traffic status information read from the VLR data analysis module and the number of vehicles entering and exiting, the road occupancy rate is predicted, and the road occupancy rate is read from the historical data storage module at the next time according to the predicted road occupancy rate. average vehicle speed and travel time. Table 1 shows the method of predicting the traffic status of this road at the next moment according to the real-time data obtained by the VLR data analysis module and the historical data of the historical data storage module.

Table 1

The specific method is as follows:

Read the real-time traffic flow N and the average speed V of vehicles on the road from the VLR data analysis module. Calculate the traffic road occupancy rate P=N/C (C is the design traffic volume), and calculate the time required for the traffic road T=L/V.

Read the historical path of the terminal from the historical data storage module, judge the driving direction of the terminal according to the historical path of the terminal, and calculate the traffic flow In that is about to enter the road on the road in the area to be predicted, and the traffic flow In that is about to leave the road on the road in the area to be predicted Traffic flow out.

Calculate the traffic flow Ni of this road at the next moment, the predicted road occupancy Pi: Ni=N+In-Out, Pi=Ni/C. According to the predicted road occupancy Pi, query the historical data storage module for the average driving of road vehicles Velocity Vi, the corresponding road occupancy rate and vehicle average driving speed are stored in the historical data storage module. Calculate the time Ti required to pass through the highway, Ti=L/Vi. That is, the server predicts the traffic state and obtains the predicted road transit time Ti. Or query the historical data storage module for the time Ti needed to pass through the highway. The historical data storage module stores the corresponding road occupancy rate and the road passage time of the vehicles to obtain the predicted road passage time Ti.

Continue to read the historical path of the terminal from the historical data storage module, judge the driving direction of the terminal according to the historical path of the terminal, and calculate the traffic flow Ini about to enter the highway and the traffic flow Outi about to leave the highway.

Repeat the above operations, and continuously predict the road speed Vi and the time Ti required to pass the road at the next moment, as shown in Table 2.

Table 2

A series of road speeds Vi and time Ti required to pass the road in the above operations are the prediction results of the current road state.

The state prediction results of each road are synthesized to obtain a traffic prediction network of the entire road traffic state changing with time.

The schematic diagram of the intelligent traffic prediction network changing with time, with the road transit time as the weight is shown in Figure 3, n=1, 2, 3...i.

Step 206. Personal navigation: For a specific user, the personal navigation module selects a reasonable route for the user according to the user's location information in the VLR analysis module, the destination information set by the user, and the traffic status predicted by the traffic prediction module.

In this way, the server can select a navigation route for the terminal according to the location information of the cell to which the terminal belongs (as the terminal's current location), the destination address, and the predicted road passing time.

During specific implementation, the personal navigation module first asks the user whether to select a destination, and if the user does not select a destination, the destinations frequently selected by the user during this time period are read by default from the historical data module.

Next, in response to the fact that the user may need to go to other places before arriving at the destination, the user is asked whether to choose a necessary place. If the user selects a necessary place, read the necessary place proposed by the user, otherwise leave it blank, and directly select the shortest path for the user's destination.

The personal navigation module reads the road state prediction map, and calculates the shortest path from the traffic intersection to any traffic intersection on the map over time as follows:

As shown in Figure 4, taking point 3 in Figure 4 as an example, the algorithm for calculating the shortest path with variable weight from point 3 to other points is as follows:

Choose the point that is directly connected to the starting point (point 3) and has the smallest weight, taking point 5 as an example, then, at time t, the shortest distance d3-5 from point 3 to point 5 is T5t.

Select the point (point 5) with the smallest weight in the previous step, and calculate the path from the starting point to other points through this point (point 5). D _3-5-4 =T5 _t +T6 _(t+T5t) and D _3-5-6 =T5 _t +T8 _(t+T5t) . Comparing the time D _3-4 from the starting point to 4 and the time D _3-5-4 passing through point 5, take min(D _3-4 , D _3-5-4 ) and update it to D _3-4 .

Repeat the above steps to calculate the shortest path from the starting point to other points.

Thus, the shortest distance in time from any point on the road to other points can be predicted at any time.

According to the user's location information, passing location information, destination information, and predicted road passing time, a path with the shortest time is selected.

If there is no passing location information, a path with the shortest time is found directly based on the user's location and destination location based on the prediction information, and the path and time of the path passing through each road, and the total time required for prediction are notified to the user. Compare this path with the user's historical path, mark the historical path as a dotted line, and calculate the time required for the historical path. Both are presented to the user for selection. Generally, if the time difference between the two is not more than 5%, users are recommended to use the historical path.

If there is passing information, first calculate the shortest path from the user's starting point to each necessary location. Then, according to the time length of the shortest path, priorities are set for different must-pass locations. The shorter the time, the higher the priority of the must-pass points.

Starting from the user's starting point, select the shortest path to the point with the highest priority, and then select the shortest path from the point with the highest priority to the point with the second highest priority, until the path is selected to reach the destination selected by the user.

Since the user's vehicle speed does not necessarily follow the average speed or traffic changes due to emergencies on the road, the time at which the user arrives at different intersections may be different from the predicted time. Therefore, the user's location and the forecast of the traffic network must be dynamically updated.

Update the traffic forecast map and the shortest path for users according to real-time traffic conditions. Prompt the user to update the path. And compare the current path with the selected path for the user to choose.

The embodiment of the present invention also provides a device for obtaining information required for traffic state prediction, including:

Position acquisition module 301: used to acquire the cell identification codes of each cell in the area to be predicted, and the location information of each cell;

Time acquiring module 302: used to acquire the identification information of terminals in each cell from the network elements storing location information in the mobile network according to the acquired cell identification code, and obtain the identification information of each terminal with the read identification information in each network respectively. The time of last registration;

Information obtaining module 303: used for obtaining information required for traffic state prediction according to the location information of each cell and the last registration time of each terminal in each network element.

Further, it also includes:

Storage module 304: used to determine and store the traffic status of the terminal in the predetermined time period according to the number of terminals in the predetermined time period, terminal moving speed, terminal moving path and the type of vehicle the terminal belongs to within a predetermined number of days before predicting the traffic state. Tool, the driving path of the vehicle, and the corresponding relationship of road occupancy rate, wherein the corresponding relationship between road occupancy rate and the parameters used to represent the traffic state prediction results, wherein the information required for traffic state prediction includes: terminal The moving speed of the terminal in the predetermined time period, the moving path of the terminal in the predetermined time period, and the vehicle type determined according to the moving speed of the terminal in the predetermined time period and the moving path of the terminal in the predetermined time period.

Real-time acquisition module 305: used to acquire real-time road traffic status information on the roads in the area to be predicted during the predetermined time period of the day when the traffic status prediction is performed;

Quantity determination module 306: used to obtain the number of vehicles that will enter and exit the road in the area to be predicted according to the stored vehicle to which the terminal belongs and the driving route of the vehicle;

Result prediction module 307: used to predict the road occupancy rate according to the real-time road traffic state information, the number of vehicles entering and leaving, and predict the traffic state according to the predicted road occupancy rate and the stored road occupancy rate correspondence, Get the prediction result.

Further, the parameter representing the traffic state prediction result is the road transit time of the vehicle;

Real-time acquisition module 305: it is also used to obtain the scheduled time period of the forecasted day according to the total number of terminals on the roads in the area to be predicted, the moving speed, moving path and vehicle type of each terminal according to the scheduled time period of the day when the traffic status is predicted. , the number N of real-time vehicles on the road in the area to be predicted;

Result prediction module 307: it is also used to calculate the predicted road occupancy rate Pi, wherein Pi=Ni/C, C is the design traffic volume, Ni=N+In+Out, and In is the number of vehicles that will enter the road in the area to be predicted , Out is the number of vehicles that will drive out on the road in the area to be predicted;

The server predicts the traffic state according to the predicted road occupancy rate Pi and the corresponding relationship between the road occupancy rate and the road passing time, and obtains the predicted road passing time.

Further, it also includes:

The reading module 308: used to read the location information of the cell to which the terminal belongs from the network element storing the location information in the mobile network according to the navigation request including the destination address reported by the terminal;

Selection module 309: for selecting a navigation route for the terminal according to the location information of the cell to which the terminal belongs, the destination address, and the predicted road passing time.

Further, the selection module 310: is also used to determine the shortest path with time variation according to the location information and destination address of the cell to which the terminal belongs, and the predicted road transit time, and use the shortest path with time variation as the navigation path selected for the terminal.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that: it still Modifications or equivalent replacements can be made to the technical solutions of the present invention, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A method for obtaining information required for traffic state prediction, characterized in that, comprising: The server reads the cell identification code CELLID of each cell in the area to be predicted and the location information of each cell from a map database. location information; According to the obtained cell identification code, the server obtains the identification information of the terminals in each cell from the network elements that store the location information in the mobile network, and obtains the last registration time of each terminal with the read identification information in each network element, respectively. The above-mentioned network element is the visitor location register VLR of the mobile network, the mobile switching center MSC, the soft switch controller, the serving GPRS support node SGSN, the mobility management entity MME, or the home subscriber server HSS; According to the location information of each cell and the last registration time of each terminal in each network element, the server obtains the information required for traffic state prediction. The information required for traffic state prediction includes: the moving speed of the terminal within a predetermined time period, the The movement path of the predetermined time period and the server determines the vehicle type to which the terminal belongs during the predetermined time period according to the movement speed of the terminal during the predetermined time period and the movement path of the terminal during the predetermined time period. 2. The method according to claim 1, further comprising: Before predicting the traffic status, the server determines and stores the vehicle to which the terminal belongs, the vehicle to which The corresponding relationship between the driving path and the road occupancy rate, wherein the corresponding relationship between the road occupancy rate is the corresponding relationship between the road occupancy rate and the parameters used to represent the traffic state prediction results; The server obtains the real-time road traffic status information on the roads in the area to be predicted during the scheduled time period of the traffic status prediction day; According to the stored vehicle to which the terminal belongs and the driving path of the vehicle, the server obtains the number of vehicles that will enter and exit the road in the area to be predicted; The server predicts the road occupancy rate according to the real-time road traffic state information and the number of vehicles entering and leaving, and predicts the traffic state according to the predicted road occupancy rate and the corresponding relationship of the stored road occupancy rate, and obtains the prediction result. 3. method according to claim 2, is characterized in that, the parameter that represents traffic state prediction result is the road transit time of vehicle; The server obtains the real-time road traffic state information on the roads in the area to be predicted for the predetermined time period of the day when the traffic state prediction is performed: According to the total number of terminals on the roads in the area to be predicted during the scheduled time period of the day when the traffic status is predicted, the moving speed, moving path and vehicle type of each terminal, the server obtains the number of terminals on the roads in the area to be predicted during the scheduled time period of the forecasted day. The number of real-time vehicles N; The server predicts the road occupancy rate according to the real-time road traffic status information, the number of vehicles entering and leaving, and predicts the traffic state according to the predicted road occupancy rate and the corresponding relationship between the stored road occupancy rate, and the prediction results are as follows: The server calculates the predicted road occupancy rate Pi, where Pi=Ni/C, Ni=N+In-Out, C is the design traffic volume, In is the number of vehicles that will enter the road in the area to be predicted, and Out is the road in the area to be predicted the number of vehicles to be driven out; The server predicts the traffic state according to the predicted road occupancy rate Pi and the corresponding relationship between the road occupancy rate and the road passing time, and obtains the predicted road passing time. 4. The method according to claim 3, further comprising: According to the navigation request including the destination address reported by the terminal, the server reads the location information of the cell to which the terminal belongs from the network element storing the location information in the mobile network; The server selects a navigation route for the terminal according to the location information of the cell to which the terminal belongs, the destination address, and the predicted road passing time. 5. The method according to claim 4, wherein the server selects a navigation path for the terminal according to the location information and destination address of the cell to which the terminal belongs, and the predicted road transit time, specifically: The server determines the time-varying shortest path according to the location information and destination address of the cell to which the terminal belongs, and the predicted road passing time, and takes the time-varying shortest path as the navigation path selected for the terminal. 6. A device for obtaining information required for traffic state prediction, characterized in that it comprises: Position acquisition module: used to read the cell identification codes of each sub-district in the area to be predicted and the location information of each sub-district from a map database, the map database includes map information of roads and each road contains the sub-district identification code of the sub-district Geographic location information corresponding to CELLID; Time acquisition module: used to obtain the identification information of the terminals in each cell from the network elements that store location information in the mobile network according to the acquired cell identification code, and obtain the identification information of each terminal with the read identification information in each network element Last registration time, the network element is the visitor location register VLR of the mobile network, the mobile switching center MSC, the soft switch controller, the serving GPRS support node SGSN, the mobility management entity MME, or the home subscriber server HSS; Information acquisition module: used to obtain the information required for traffic state prediction according to the location information of each cell and the last registration time of each terminal in each network element, the information required for the traffic state prediction includes: The moving speed, the moving path of the terminal in the predetermined time period, and according to the moving speed of the terminal in the predetermined time period and the moving path of the terminal in the predetermined time period, determine the vehicle type to which the terminal belongs in the predetermined time period. 7. The device according to claim 6, further comprising: Storage module: used to determine and store in the predetermined time period, the vehicle to which the terminal belongs according to the number of terminals, terminal moving speed, terminal moving path and the type of vehicle to which the terminal belongs within a predetermined number of days before predicting the traffic state. , the corresponding relationship between the driving path of the vehicle and the road occupancy rate, wherein the corresponding relationship between the road occupancy rate is the corresponding relationship between the road occupancy rate and the parameters used to represent the traffic state prediction results; Real-time acquisition module: used to obtain real-time road traffic status information on the roads in the area to be predicted during the scheduled time period of the traffic status prediction day; Quantity determination module: used to obtain the number of vehicles that will enter and leave the road in the area to be predicted according to the stored vehicle to which the terminal belongs and the driving path of the vehicle; Result prediction module: it is used to predict the road occupancy rate according to the real-time road traffic state information, the number of vehicles entering and leaving, and predict the traffic state according to the predicted road occupancy rate and the corresponding relationship of the stored road occupancy rate, and obtain forecast result. 8. The device according to claim 7, characterized in that, the parameter representing the traffic state prediction result is the road transit time of the vehicle; Real-time acquisition module: it is also used to predict the scheduled time period of the day according to the traffic status prediction, the total number of terminals on the road in the area to be predicted, the moving speed, moving path and vehicle type of each terminal, and obtain the scheduled time period of the forecasted day, The number of real-time vehicles N on the road in the area to be predicted; Result prediction module: it is also used to calculate the predicted road occupancy rate Pi, wherein Pi=Ni/C, C is the design traffic volume, Ni=N+In-Out, In is the quantity that will enter the vehicle on the road to be predicted area, Out is the number of vehicles that will drive out on the road in the area to be predicted; The server predicts the traffic state according to the predicted road occupancy rate Pi and the corresponding relationship between the road occupancy rate and the road passing time, and obtains the predicted road passing time. 9. The device according to claim 8, further comprising: Reading module: used to read the location information of the cell to which the terminal belongs from the network element storing the location information in the mobile network according to the navigation request including the destination address reported by the terminal; Selection module: used to select a navigation route for the terminal according to the location information and destination address of the cell to which the terminal belongs, as well as the predicted road passing time. 10. The device according to claim 9, characterized in that the selection module is further used to determine the shortest path that changes in time according to the location information and destination address of the cell to which the terminal belongs, and the predicted road passing time, and change the time to The shortest path of is used as the navigation path chosen for the terminal.