TWI799318B - Apparatus and method for analyzing traffic status and computer program product implementing the method - Google Patents

Abstract

An apparatus and a method for analyzing traffic status, and a computer program product for implementing the method are provided. Firstly, a batch analysis filtering is performed on a plurality of mobile signaling data of a plurality of mobile devices received, so as to generate a plurality of mobile signaling location data. Then, the plurality of mobile signaling location data is mapped to a roadway, so as to calculate a total sample volume of the roadway, interval sample volumes and their respective corresponding hourly speed of the roadway. Afterward, based on the total sample volume of the roadway and a congestion threshold of the roadway calculated from historical data of the roadway, a sample group being selected of the total sample volume is determined. Finally, an aggregation is performed on the interval sample volumes and their respective corresponding hourly speed within the selected sample group, thereby quickly and precisely generating real-time hourly speed information of the roadway.

Description

Equipment, method and computer program product for analyzing road conditions

This case is about a traffic condition analysis technology, in detail, it is about the equipment, method and computer program product for analyzing congested road conditions using mobile signaling data.

In recent years, Cellular-Based Vehicle Probe (CVP) technology based on mobile device base stations has been widely used in the detection of road traffic information due to its wide coverage and low cost. Generally speaking, CVP technology mainly uses mobile phone signaling, that is, calculates the average vehicle speed and travel time on the road section by using the time difference and position difference of CVP signaling data.

However, since the mobile signaling road condition analysis technology analyzes the road conditions through the time and location of the mobile signaling points, it will be affected by signaling drift and different vehicles. For example, signaling drift is often unavoidable due to the limitation of base station positioning technology, but this problem will affect the correctness of road condition analysis, especially when there is congestion, the position of signaling will drift more easily and become unstable, resulting in inaccurate road condition analysis. precise. On the other hand, means of transport usually need to use heterogeneous data for verification, such as public transport schedules, ticket information, image recognition information, etc., which only increases the complexity of the system or calculation.

Therefore, how to use the mobile signaling data to quickly and accurately analyze the congested road conditions is an issue to be solved at present.

In order to solve the above-mentioned problems and other problems, this case discloses a device, method, computer program product and computer-readable recording medium for analyzing road conditions.

The equipment disclosed in this case for analyzing road conditions includes: a data receiving module for receiving multiple mobile signaling data from multiple mobile devices; a batch filtering module for receiving multiple mobile signaling data from multiple mobile devices; Perform batch analysis and filtering on the data to generate multiple mobile signaling location data; the section correspondence module maps the multiple mobile signaling location data to a road section to calculate the total sample size of the road section and the multiple interval samples and the speed per hour corresponding to the sample size of each section; and the dynamic congestion threshold calculation module, which calculates the congestion threshold of the road section according to the historical data of the road section; the dynamic congestion detection module, which calculates the congestion threshold value of the road section according to the The congestion threshold and the total sample size of the road section determine the sample group selected in the total sample size; and the speed aggregation module performs speed aggregation for each interval sample size and its corresponding speed in the selected sample group , so as to generate real-time speed information of the road section.

In one embodiment, the batch filtering module of this case cuts the plurality of mobile signaling data in batches according to time sequence, so as to perform principal component analysis, direction filtering and distance filtering on the mobile signaling data of each batch, After the batches of the mobile signaling data are subjected to principal component analysis, direction filtering and distance filtering, each batch of mobile signaling location data is generated to form the plurality of mobile signaling location data.

In one embodiment, the dynamic congestion detection module of this case compares the total sample size with the congestion threshold value, so as to select a faster sample group when the total sample size is not greater than the congestion threshold value, and in the When the total sample size is greater than the congestion threshold, it is judged whether the low-speed proportion of the road section is greater than the low-speed proportion threshold value of the road section calculated based on the historical data of the road section, so that the low-speed proportion is not greater than the low-speed proportion. When the threshold value is exceeded, a sample group with a faster speed is selected, and when the low-speed ratio is greater than the low-speed ratio threshold value, a larger sample group is selected.

In one embodiment, the speed aggregation module of this case performs weighted average of the low speed value and the speed probability value of each interval in the selected sample group, so as to generate real-time speed information of the road section.

The method for analyzing road conditions disclosed in this case includes: performing batch analysis and filtering on multiple mobile signaling data received from multiple mobile devices to generate multiple mobile signaling location data; The location data is corresponding to a road section to calculate the total sample size of the road section, the sample size of multiple intervals, and the speed per hour corresponding to the sample size of each interval; calculated based on the total sample size of the road section and the historical data of the road section The congestion threshold of the road section is determined to determine the selected sample group in the total sample size; and the speed aggregation is performed on the sample size of each interval in the selected sample group and the corresponding speed to generate real-time speed information of the road section .

In one embodiment, the step of performing batch analysis and filtering on the multiple mobile signaling data received from multiple mobile devices to generate multiple mobile signaling location data includes: cutting the mobile signaling data in batches according to time sequence A plurality of mobile signaling data; principal component analysis, direction filtering and distance filtering are performed on each batch of mobile signaling data; and principal component analysis, direction filtering and distance filtering are performed on the mobile signaling data of each batch Afterwards, each batch of mobile signaling location data is generated to form the plurality of mobile signaling location data.

In one embodiment, according to the total sample size of the road section and the congestion threshold value of the road section calculated according to the historical data of the road section described in this case, the steps of determining the selected sample group in the total sample size include: : compare the total sample size with the congestion threshold, wherein, when the total sample size is not greater than the congestion threshold, select the faster sample group, and when the total sample size is greater than the congestion threshold, judge the Whether the low-speed ratio of the road section is greater than the low-speed ratio threshold value of the road section calculated based on the historical data of the road section, wherein, when the low-speed ratio is not greater than the low-speed ratio threshold value, select samples with faster speeds group, and when the low-speed ratio is greater than the low-speed ratio threshold value, a larger sample group is selected.

In one embodiment, the step of selecting a faster sample group as described in this case includes: calculating the sample size of the first N intervals/the total sample size and N/the total interval number from fast to slow; The interval sample size/the total sample size is greater than or equal to the N/total interval number, and the group with the sample size of the first N intervals is selected as the faster sample group.

In one embodiment, the step of selecting a large number of sample groups as described in this case includes: dividing adjacent M intervals into a group to calculate the sum of the sample sizes of each group; The group of the quantity is the sample group with a larger number.

In one embodiment, the step of performing speed aggregation on the sample size of each interval in the selected sample group and its corresponding speed to generate the speed information of the road section described in this case includes: The low value of speed per hour and the probability value of speed per hour are weighted and averaged to generate real-time speed per hour information of the road section.

The computer program product for analyzing road conditions disclosed in this case can be downloaded to a computer to implement the method disclosed above for analyzing road conditions.

The computer-readable recording medium for analyzing road conditions disclosed in this case can be downloaded through the computer to implement the method disclosed above for analyzing road conditions.

Using the equipment, method, computer program product and computer-readable recording medium disclosed in this case to analyze the condition of the road section, perform batch analysis and filtering to filter out drifting points, and then map the mobile signaling position data to the road section, and then Implement congestion threshold calculation and dynamic congestion detection technology to track changes in speed over time and avoid situations that do not match the actual road conditions. Therefore, it is possible to quickly and accurately analyze whether the road conditions are congested or smooth without additional interrogation of heterogeneous data. Improve the accuracy of traffic analysis.

10: Base station

2: Equipment

21: Data receiving module

22:Batch filter module

23: Road section corresponding module

24: Dynamic congestion threshold calculation module

25: Dynamic congestion detection module

26: Speed aggregation module

30: Database

P1~P12: point

S201~S206: steps

S301~S304: steps

S401~S406: steps

Fig. 1 is a schematic diagram of the structure of an embodiment of the equipment for analyzing road section conditions according to the present application.

Fig. 2 is a schematic flow chart of an embodiment of the method for analyzing road section conditions according to the present application.

FIG. 3A is a schematic diagram of an embodiment of batch analysis and filtering in the method for analyzing road conditions in this case.

Fig. 3B is a schematic diagram of an embodiment of principal component analysis in the method for analyzing road conditions in this case.

Fig. 4 is a schematic diagram of an embodiment of group selection in the method for analyzing road section conditions in this case.

Fig. 5 is a schematic diagram of an embodiment of the interval sample size and the corresponding speed per hour in the method for analyzing road section conditions in this case.

Fig. 6 is a schematic diagram of an embodiment of selecting a fast group in the method for analyzing road conditions in this case.

Fig. 7 is a schematic diagram of an embodiment of selecting a large group in the method for analyzing road conditions in this case.

The implementation of this case is described below through specific examples, and those skilled in this art can easily understand other advantages and effects of this case from the content disclosed herein. The structures, ratios, sizes, etc. shown in the drawings attached to this manual are only used to match the content disclosed in the manual, for the understanding and reading of those who are familiar with this technology, and are not used to limit the conditions that can be implemented in this case. Therefore, any modifications, changes or adjustments should still fall within the scope covered by the technical content disclosed in this case without affecting the functions and goals that can be achieved in this case.

Please refer to Figure 1, the device 2 in this case includes a data receiving module 21, a batch filtering module 22, a road section corresponding module 23, a dynamic congestion threshold calculation module 24, a dynamic congestion detection module 25, and an hourly speed aggregation module 26.

In one embodiment, the device 2 is a remote or cloud server. In another embodiment, each module in Fig. 1 can be software, hardware or firmware; if it is hardware, it can be a processing unit, processor, computer with data processing and computing capabilities; if it is Software or firmware may include processing units, processors, and computer-executable instructions.

The data receiving module 21 receives a plurality of mobile signaling data of a plurality of mobile devices from the base station 10 . Specifically, the mobile device can be, for example, a smart phone, a smart watch, a tablet computer, etc. with a SIM (Subscriber Identity Module) card. Mobile signaling data are transmitted between the base stations 10, including such data as the location, time and speed of the mobile device. In a specific embodiment, the action signaling data is, for example, CVP signaling data.

The batch filtering module 22 batches, analyzes and filters the mobile signaling data of the mobile devices received by the data receiving module 21 to generate a plurality of mobile signaling location data. Specifically, for a mobile device, the batch filtering module 22 accumulates a plurality of mobile signaling data in chronological order, and cuts them into batches after accumulating to a certain amount, and then uses principal components analysis (principal components analysis) for the batch , PCA) method to analyze the principal components of the batch of points, and then perform direction filtering and distance filtering, and then filter out the points that are opposite to the moving direction of the principal components or that are too far away from the principal components. Then, a part of the filtered points is imported into the road section corresponding module 23, and another part is reserved as the first few points of the next batch, so as to continue to use the principal component analysis method and direction filtering and distance filtering, and so on. Moreover, the batch filtering module 22 performs the above-mentioned processes such as chronological accumulation, batch cutting, principal component analysis, direction filtering and distance filtering on the plurality of mobile signaling data of each mobile device, and the mobile signaling of each batch After the data is processed, the data transmitted to the corresponding module 23 of the road section is the plurality of mobile signaling location data.

The road section corresponding module 23 corresponds the plurality of mobile signaling location data generated by the batch filtering module 22 to a road section to calculate the total sample size of the road section, the plurality of interval sample sizes and the corresponding speed per hour. Specifically, the locations of multiple user devices can be calculated based on multiple action signals, combined with the road network information, the number of all user devices on the road section (that is, the total sample size) can be obtained, and cut according to the speed limit of the road section A plurality of speed intervals are generated, and each speed interval has its corresponding number of user devices (that is, the sample size of the plurality of intervals and the corresponding speed). It should be noted that, since the batch filtering module 22 continuously executes chronological accumulation, batch switching cutting, principal component analysis, direction filtering, and distance filtering, etc., and then transmit the plurality of action signaling position data to the road section corresponding module 23, so the total sample size of the road section calculated by the road section corresponding module 23, the plurality of The interval sample size and the corresponding hourly speed also change with the time series.

The dynamic congestion threshold calculation module 24 calculates the congestion threshold of the road section according to the historical data of the road section in the database 30 . Specifically, the database 30 stores road network information, road capacity data, and historical data, etc., wherein the historical data, for example, at intervals (such as every five minutes) in the history of the same period of time on the road section (such as the past seven days) For the total historical sample size, the dynamic congestion threshold calculation module 24 selects about ten samples with the largest total sample size, and an average of about 60% is used as the congestion threshold. In addition, if there is no sample information of the past few days, the dynamic congestion threshold calculation module 24 can set the road capacity of the road segment in the database 30 as the congestion threshold. In addition, the dynamic congestion threshold calculation module 24 calculates the low-speed ratio threshold value of the road section according to the historical data of the road section, and can also select about 80% of the average speed per hour of every five minutes in the past seven days in the same period of time on the road section as the low-speed threshold, and then calculate The ratio of the sample size below the low-speed threshold to the total historical sample size is used as the low-speed ratio threshold.

The dynamic congestion detection module 25 determines the total sample size according to the congestion threshold of the road section and the total sample size of the road section, or according to the low-speed ratio threshold value of the road section and the low-speed ratio of the road section. The selected sample group. In one embodiment, the dynamic congestion detection module 25 compares the total sample size of the road section with the congestion threshold value of the road section, and if the total sample size of the road section calculated by the road section corresponding module 23 is not greater than (i.e. less than or equal to) the congestion threshold calculated by the dynamic congestion threshold calculation module 24, then the dynamic congestion detection module 25. judges that there are few or smooth vehicles, so the dynamic congestion detection module 25 determines from the total sample size Select the faster sample group. In another embodiment, if the total sample size of the road section calculated by the road section corresponding module 23 is greater than the dynamic The congestion threshold calculated by the congestion threshold calculation module 24 is judged by the dynamic congestion detection module 25 as having too many vehicles or congestion, and then the dynamic congestion detection module 25 compares the low-speed ratio of the road section with the low-speed ratio of the road section. than the threshold. If the low-speed proportion of this road section calculated by the corresponding module 23 of the road section is not greater than (i.e. less than or equal to) the low-speed ratio threshold value of this road section calculated by the dynamic congestion threshold calculation module 24, then there may be many cars but the vehicle speed If it is fast enough, the congestion condition is not yet met, so the dynamic congestion detection module 25 decides to select a faster sample group from the total sample size. If the low-speed proportion of the road section calculated by the corresponding module 23 of the road section is greater than the low-speed ratio threshold value of the road section calculated by the dynamic congestion threshold calculation module 24, there may be many cars and the speed is slow, which should be regarded as satisfying the congestion condition, so the dynamic congestion detection module 25 decides to select a larger number of sample groups from the total sample size.

The speed aggregation module 26 aggregates the sample size and the corresponding speed of each interval in the sample group selected by the dynamic congestion detection module 25, that is, the low speed value and the speed probability of each interval in the selected sample group Values are weighted and averaged to generate real-time speed information of the road section, wherein the speed probability value refers to the sample size of an interval compared to the sample size of the selected sample group. In addition, the generated real-time speed information of the segment will also be transmitted to the database 30 as an update basis for subsequent calculation of the congestion threshold.

Therefore, the device 2 in this case includes a data receiving module 21, a batch filtering module 22, a road section corresponding module 23, a dynamic congestion threshold calculation module 24, a dynamic congestion detection module 25 and a speed aggregation module 26 , receiving the action signaling data from the base station 10, performing batch analysis and filtering to filter out drift points, iteratively tracking the change of the speed with time sequence, and calculating the dynamic threshold value according to the historical data of the corresponding road section in the database 30 to thereby Carry out dynamic congestion detection. In traffic conditions with low traffic flow, select faster sample groups to reduce the influence of slow speed calculation results caused by sampling a small number of slow vehicles. In traffic conditions with medium to high traffic volume, further study Consider vehicle speed data to increase the judgment conditions of congested road conditions, and introduce a dynamic update mechanism for road congestion thresholds to avoid situations that do not match the actual road conditions due to the use of basic fixed data on road sections, so as to improve the accuracy of road condition analysis.

In one embodiment, the data generated by the above-mentioned modules in this case can be used for subsequent applications of various traffic services, and can be presented through an APP or a webpage for early road diversion or release of traffic measures to avoid road congestion, thereby saving travel time. In another embodiment, the above-mentioned modules of this case can also be disassembled separately, such as the processing performed by the batch filtering module, in which the number and proportion of drifting points can be captured, and can also be applied to the stop points later , accident detection and other technologies; as for the processing performed by the dynamic congestion detection module, the judgment of congested road conditions can be used to label the degree of road congestion, and the labeling data is used as one of the attributes to be applied to other traffic analysis services.

Please refer to FIG. 2 , the method for analyzing road conditions in this case mainly includes steps S201 to S206 , which are mainly executed by the device 2 in FIG. 1 .

In step S201, a plurality of mobile signaling data of a plurality of mobile devices are received from the base station, and then proceed to step S202.

In step S202, batch analysis and filtering are performed on the mobile signaling data of the mobile devices to generate the mobile signaling location data. The steps of batch analysis and filtration are shown in Figure 3A in detail, including steps S301-S304.

In step S301, batch cutting is performed. In detail, multiple mobile signaling data for each mobile device are accumulated in chronological order, and after a certain amount is accumulated, they are divided into batches, such as batch 1, and then proceed to step S302.

In step S302, principal component analysis is performed. In detail, principal component analysis is performed on multiple points of batch 1 (that is, the action signaling data), as shown in Figure 3B, in which a batch contains There are 12 points P1~P12, the point numbers represent the sequence of point time, the principal components found by the principal component analysis method are shown by the arrows, and then go to step S303.

In step S303, direction filtering and distance filtering are performed. As shown in Figure 3B, among the 12 points, it can be seen that the parallel movement directions of points P5 and P6 do not match the principal components, while the vertical distances between points P2, P4, P9, and P10 and the principal components are too large, so filtering After that, there are only 6 points P1, P3, P7, P8, P11, and P12 left, and then proceed to step S304.

In step S304, the filtered point group is retained, and some points are reserved for the next batch. Specifically, the last 30% points of batch 1, that is, points P11 and P12 will be reserved as the first two of the next batch, so the points of batch 2 are P11, P12, P13, P14, ..., batch 3 is also generated by analogy. Therefore, the filtered point group 1 includes four points P1, P3, P7, and P8, that is, as the action signaling position data, and the filtered point group 2 and 3 are also generated by analogy, so the included points That is, as the mobile signaling location data, then proceed to step S203.

In step S203, a plurality of mobile signaling location data are mapped to road sections, and then proceed to step S204.

In step S204, the total sample size of the road section, the sample size of multiple intervals and the corresponding speed per hour are calculated, and then proceed to step S205. In a specific embodiment, please refer to FIG. 5 , take a speed limit of 80 road section speed sample distribution as an example, the speed per hour is allowed to the speed limit+20, so the speed per hour interval is cut by (80+20)/5, so by Figure 5 shows the sample size as the vertical axis and the speed interval as the horizontal axis. It can be seen that the total sample size of the road section at the current time, the sample size of multiple intervals and the corresponding speed per hour.

In step S205, according to the total sample size of the road section and the congestion threshold value calculated according to the historical data of the road section, the selected sample group in the total sample size is determined. Specific facts Please refer to FIG. 4 , the group selection method in the method for analyzing road section conditions in this case includes steps S401-S406.

In step S401, the congestion threshold of the road section is calculated. In one embodiment, the calculation formula of the congestion threshold is as follows:

Congestion threshold = AVG (peak sample size) * 0.6

In one embodiment, the peak value of the sample size: based on the current time, push back the sample size of each five minutes within seven days, and take the ten sample sizes with the largest sample size. Therefore, the congestion threshold is 60% of the sample peak average in the last seven days. If there is no sample information within seven days, the road capacity of the road section is used as the congestion threshold.

In step S402, it is determined whether the total sample size of the road section is greater than the congestion threshold of the road section. If the total sample size is not greater than the congestion threshold, it can be considered that there are few or smooth vehicles, and the process goes to step S403. If the total sample size is greater than the congestion threshold, it can be considered that there are too many vehicles, and the process goes to step S405.

In step S403, a sample group with a faster time velocity is selected. In one embodiment, assuming that the total sample size of the road section is 407, the fast group selection method is as follows.

(Sample size of the first N intervals from fast to slow/total sample size)>=N/Number of intervals.

See Figure 6.

N=1, 4/407<1/20

N=2，(4+8)/407<2/20

N=3，(4+8+7)/407<3/20

…

N=12, (4+8+7+10+10+8+16+16+41+38+57+31)/407>12/20

In other words, the interval of N=1~12 is the sample group with a faster speed, as shown in the box in Figure 6, it is the selected sample group, which is used as the basis for the subsequent calculation of the real-time speed information of the road section.

In step S405, it is determined whether the low-speed ratio of the road section is greater than the low-speed ratio threshold value of the road section. Before that, in step S405, the low-speed ratio threshold value of the section is calculated.

The low-speed ratio threshold is calculated as follows:

In one embodiment, assuming that the average speed of the road section in the past 7 days is 70, then the low-speed threshold is 70*0.8=56, then based on the current time of the road, the threshold of low-speed proportion in the past seven days = the number of low-speed samples in the past seven days/ Total sample size for the past seven days.

In addition, as shown in Figure 7, assuming that in this example, the total sample size is 407, there are 292 samples with a speed lower than 56kph, and Figure 7 shows that there are 287 samples in the range of 0-55 per hour, then the road section is currently The ratio of low speed is 287/407 (about 0.7).

If the low-speed ratio is not greater than the low-speed ratio threshold, it can be considered that there are many vehicles but the vehicle speed is not slow, and the process proceeds to step S403. If the low-speed ratio is greater than the low-speed ratio threshold, it can be considered that there are many and slow vehicles and the congestion condition is met, and the process goes to step S406.

In step S406, a larger sample group is selected. In one embodiment, assuming that the total sample size of the road section is 407, the large group selection method is as follows: M adjacent sections are divided into one group, and the group with the highest total sample size of the speed intervals is the large group. If more than one group has the highest total sample size, select the group with a lower speed.

As shown in Figure 7, in one embodiment, three adjacent intervals are divided into one group, then it can be seen that the interval sample size of the group formed by the speed intervals 35-40, 40-45, and 45-50 has the highest total sum, This is a large group, as shown in the box in Figure 7, is the selected sample group, which is used as the basis for subsequent calculation of the real-time speed information of this road section.

After completing the selection of sample groups in the above step S205 (including steps S401~S406), proceed to step S206.

In step S206, speed aggregation is performed on the sample size of each interval in the selected sample group and the corresponding speed, so as to quickly and accurately generate real-time speed information of the road section. Specifically, the weighted average of the low speed per hour and the probability of speed per hour of each interval in the selected sample group is carried out to generate the real-time speed per hour information of this road section, wherein:

In one embodiment, if the fast group is selected, refer to Fig. 6, the fast group shown in the box has a total of 246 samples in 12 intervals, and the hourly aggregation is as follows:

(4/246)*95+(8/246)*90+(7/246)*85+(10/246)*80+(10/246)*75+(8/246)*70+(16 /246)*65+(16/246)*60+(41/246)*55+(38/246)*50+(57/246)*45+(31/246)*40=55.96

Therefore, in this embodiment, because the total sample size of this road segment is less than the congestion threshold value in the current period, or although the total sample size is more than the congestion threshold value but the proportion of low speed is still less than the low speed threshold value, the fast group is selected, and the calculated The instant speed during this period is 55.96kph.

In another embodiment, if a large group is selected, refer to Fig. 6, the large group shown in the box has a total of 136 samples in 3 intervals, and the hourly aggregation is as follows:

(48/136)*35+(31/136)*40+(57/136)*45=40.33

Therefore, in this embodiment, since the total sample size of the road segment is more than the congestion threshold value and the proportion of low speed is also more than the low speed threshold value at the current time period, a large group is selected, and the calculated real-time speed of this time period is 40.33kph.

It should be noted that, the method of the present invention can be implemented in a single or multiple sets of equipment such as servers, computers or other functions such as data processing, computing, storage, network communication, etc., wherein the server, computer Or the equipment includes a central processing unit, a hard disk, a memory, and the like.

In addition, the computer program product of the present invention executes the method after the program is loaded into the computer, and the computer-readable recording medium (such as hard disk, floppy disk, optical disk, USB flash drive) of the present invention stores the computer program product . In addition, computer program products can also be directly transmitted and provided on the Internet, so computer program products refer to things that contain programs that can be read by computers and are not limited to external forms.

In addition, the present invention also provides a computer-readable recording medium, which is applied to a computing device or computer with a processor and/or memory, and the computer-readable recording medium stores instructions, and the computing device or computer can be used to Executing the computer-readable recording medium through the processor and/or memory, so as to execute the above method and/or content when executing the computer-readable recording medium.

To sum up, this case discloses a device, method and computer program product for analyzing road conditions. It uses mobile signaling data to analyze congested road conditions, and then performs steps such as signaling reception, drift signaling filtering, road section correspondence, and speed calculation. The vector is found through the moving direction of the batch points by the principal component filtering method, and the points that do not conform to the directionality of the vector are regarded as drifting points. In terms of reducing the impact of vehicles, after the road section is mapped and before the speed of the road section is calculated, use the historical data signaling sample number, vehicle speed data or road capacity to determine whether the current traffic flow and speed meet the congestion characteristics, so there is no need to use heterogeneous data By performing cross-checking, the signaling can be grouped and grouped through the mobile characteristics of the mobile signaling itself, and then the sample group used for the final speed calculation can be adjusted, thereby improving the accuracy of road condition analysis.

The above-mentioned embodiments are only illustrative of the effects of this case, and are not used to limit this case. Modifications and changes are made. Therefore, the scope of protection of rights in this case should be listed in the scope of patent application described later.

10: Base station

2: Equipment

21: Data receiving module

22:Batch filter module

23: Road section corresponding module

24: Dynamic congestion threshold calculation module

25: Dynamic congestion detection module

26: Speed aggregation module

30: Database

Claims (8)

A device for analyzing the condition of a road section, including: a data receiving module for receiving a plurality of mobile signaling data from a plurality of mobile devices; a batch filtering module for receiving the plurality of mobile signaling data from a plurality of mobile devices Carry out batch analysis and filtering to generate a plurality of mobile signaling location data; the section correspondence module maps the plurality of mobile signaling location data to a road section to calculate the total sample size of the road section, the plurality of interval sample sizes, And the speed per hour corresponding to the sample size of each section; the dynamic congestion threshold calculation module calculates the congestion threshold value of the road section according to the historical data of the road section; the dynamic congestion detection module calculates the congestion threshold value of the road section according to the congestion threshold value of the road section and the total sample size of the road section to determine the selected sample group in the total sample size, wherein the dynamic congestion detection module compares the total sample size with the congestion threshold, so that if the total sample size is not greater than When the congestion threshold is selected, the sample group with a faster speed is selected, and when the total sample size is greater than the congestion threshold, it is judged whether the low-speed ratio of the road section is greater than the low-speed ratio of the road section calculated based on the historical data of the road section. Comparing the threshold value, to select a sample group with a faster speed when the low-speed ratio is not greater than the low-speed ratio threshold value, and select a larger number of sample groups when the low-speed ratio is greater than the low-speed ratio threshold value; and The speed aggregation module performs speed aggregation on the sample size of each interval in the selected sample group and the corresponding speed, so as to generate real-time speed information of the road section. The device as described in claim 1, wherein the batch filtering module batch-cuts the plurality of mobile signaling data in time order, so as to perform principal component analysis and direction filtering on each batch of mobile signaling data and distance filtering, so that the action signaling data of each batch is passed through the master After component analysis, direction filtering and distance filtering, each batch of mobile signaling location data is generated to form the plurality of mobile signaling location data. The device as described in claim 1, wherein the speed aggregation module performs weighted average of the low speed value and the speed probability value of each interval in the selected sample group, so as to generate real-time speed information of the road section. A method for analyzing the condition of a road segment, comprising: performing batch analysis and filtering on multiple mobile signaling data received from multiple mobile devices to generate multiple mobile signaling location data; using the multiple mobile signaling location data Corresponding to a road section to calculate the total sample size of the road section, the sample size of multiple intervals, and the speed per hour corresponding to the sample size of each interval; based on the total sample size of the road section and the historical data of the road section. The congestion threshold of the road section determines the selected sample group in the total sample size, and further includes comparing the total sample size with the congestion threshold value, wherein, when the total sample size is not greater than the congestion threshold value, the speed per hour is selected Faster sample group, and when the total sample size is greater than the congestion threshold, it is judged whether the low-speed ratio of the road section is greater than the low-speed ratio threshold value of the road section calculated based on the historical data of the road section, wherein, When the low-speed ratio is not greater than the low-speed ratio threshold, select a faster sample group, and when the low-speed ratio is greater than the low-speed ratio threshold, select a larger sample group; and for the selected The sample size of each interval in the sample group and the corresponding speed are aggregated to generate real-time speed information of the road section. The method as described in Claim 4, wherein, the step of performing batch analysis and filtering on the multiple mobile signaling data received from multiple mobile devices to generate multiple mobile signaling location data includes: chronological order Batch cutting the plurality of mobile signaling data; performing principal component analysis, direction filtering and distance filtering on the mobile signaling data of each batch; and performing principal component analysis and direction filtering on the mobile signaling data of each batch After filtering and distance filtering, each batch of mobile signaling location data is generated to form the plurality of mobile signaling location data. The method as described in claim 4, wherein the step of selecting a sample group with a faster time speed includes: calculating the sample size of the first N intervals/the total sample size and N/total number of intervals from fast to slow; and When the sample size of the first N intervals/the total sample size is greater than or equal to the N/total interval number, the group with the sample size of the first N intervals is selected as the faster sample group; The step of having a large number of sample groups includes: dividing M adjacent intervals into a group to calculate the sum total of the sample sizes of each group; As in the method described in claim 4, the step of performing speed aggregation on the sample size of each interval in the selected sample group and its corresponding speed to generate the speed information of the road section includes: each of the selected sample groups The low speed per hour value of the section is weighted and averaged with the speed probability value to generate real-time speed information of the road section. A computer program product, downloaded by a computer to execute the method described in any one of claims 4-7.

Images