CN108597224B - Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data - Google Patents
Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data Download PDFInfo
- Publication number
- CN108597224B CN108597224B CN201810410574.4A CN201810410574A CN108597224B CN 108597224 B CN108597224 B CN 108597224B CN 201810410574 A CN201810410574 A CN 201810410574A CN 108597224 B CN108597224 B CN 108597224B
- Authority
- CN
- China
- Prior art keywords
- data
- time
- traffic
- space
- facilities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Abstract
The invention provides a method and a system for identifying traffic facilities to be improved based on space-time trajectory data, which are used for acquiring mobile phone signaling data and floating car data, respectively preprocessing the mobile phone signaling data and the floating car data, and generating signaling data to be processed and car data to be processed; extracting active points from signaling data to be processed to obtain active point track data, and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to a preset data analysis rule to finally obtain a traffic facility utilization measurement index; and obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes, and identifying the traffic facilities to be improved. The method and the system of the invention utilize the multisource space-time trajectory data such as the mobile phone signaling data, the vehicle GPS data and the like to establish the traffic facility utilization measurement index, quantitatively evaluate the adaptability of group activities and traffic facilities and identify the traffic facilities to be improved.
Description
Technical Field
The invention relates to the technical field of traffic state data processing, in particular to a method and a system for identifying traffic facilities to be improved based on space-time trajectory data.
Background
With the expansion of urban space and the improvement of urban functions, the rapid development of urban social economy and the continuous growth of population and automobiles, the urban traffic facility utilization problem is increasingly highlighted, and the problems of traffic jam, frequent traffic accidents, uneven resource utilization rate and the like emerge. The important reason is the inadequate adaptation of transportation facilities to human activities. Whether the layout and the utilization of urban traffic facilities can ensure the efficient operation of traffic is related to the exertion of urban functions and the quality of life of people.
The traditional urban traffic facility analysis mainly takes static traffic network data as a main part, examines the effect and the quality of traffic network layout from the aspect of things and lacks data evidence of interaction of real activities and traffic facilities. The explosion of spatiotemporal trajectory data provides historical opportunities for dynamic transportation facility utilization assessment. By extracting large-scale real travel activities from the time-space trajectory data, a mapping relation between activity time-space intensity and transportation facility utilization can be constructed, so that the real utilization of the transportation facility is evaluated, the adaptability of group activities and the transportation facility is measured, and the transportation facility to be improved is identified.
Therefore, the prior art is subject to further improvement.
Disclosure of Invention
In view of the defects in the prior art, the invention aims to provide a method and a system for identifying a to-be-improved traffic facility based on space-time trajectory data, so as to overcome the defects that data of interaction between real activities and the traffic facility is lacked, the real utilization rate of the traffic facility cannot be evaluated and calculated, and the to-be-improved traffic facility cannot be improved in time in the prior art.
The first embodiment of the invention provides a method for identifying a to-be-improved traffic facility based on space-time trajectory data, which comprises the following steps:
step A, acquiring mobile phone signaling data and floating car data, and respectively preprocessing the mobile phone signaling data and the floating car data to generate to-be-processed signaling data and to-be-processed car data which correspond to a specific format;
b, extracting active points from the signaling data to be processed according to preset time and space rules to obtain active point track data, and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to preset data analysis rules;
step C, obtaining a traffic facility utilization measurement index according to the moving point track data and the traffic facility flow space-time matrix;
and D, obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes, and identifying the traffic facilities to be improved.
Optionally, the step of preprocessing the mobile phone signaling data and the floating car data in the step a includes:
step A1, performing quality cleaning on the mobile phone signaling data, removing repeated data, removing data with missing attributes, removing data with space time and space not in a preset range, and removing user data with user point quantity smaller than or larger than a certain threshold value to obtain preprocessed signaling data;
a2, performing quality cleaning on floating car data, removing repeated data, removing data with missing attributes, removing data with space and time not within a preset range, and performing mean value completion according to sampling frequency and adjacent sampling data to obtain preprocessed car data;
step A3, converting the spatial resolution of the preprocessed signaling data according to the resolution of the preset regular grid scale to obtain the signaling data to be processed sampled based on the preset regular grid scale;
and A4, removing data deletion which is not in the preset sampling frequency range in the preprocessed vehicle data, and converting the preprocessed vehicle data into the vehicle data to be processed sampled at equal time intervals according to the preset frequency.
Optionally, the step B of extracting the active point from the signaling data to be processed according to a rule of preset time and space, and obtaining the trajectory data of the active point further includes:
b11, sequencing the signaling data to be processed according to a preset sequencing rule to obtain an individual time sequence track;
step B12, calculating the time of entering and leaving each grid according to the individual time sequence track, and setting the first position point of the individual entering as the first active point in the active point track;
step B13, calculating the space distance and the time difference value between each position point in the individual time sequence track and the existing active point, if the space distance is smaller than a set threshold value and the time difference value is smaller than a first threshold value, adding the position point into the active point, otherwise, setting the position point as a new active point until all the position points in the individual time sequence track are completely calculated, and obtaining a candidate active point track;
and step B14, acquiring candidate active points in the candidate active point track, and when detecting that the difference value between the entering time and the leaving time of the candidate active points is smaller than a second set threshold, removing the corresponding candidate active points from the candidate active point track to generate active point track data.
Optionally, the obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to a preset data analysis rule in the step B includes:
step B21, dividing the data of the vehicle to be processed into at least two characteristic day data according to the acquisition time of the data of the floating vehicle, dividing each characteristic day data into a plurality of time intervals, and taking each time interval as an observation time point;
and B22, constructing a traffic facility flow space-time matrix according to the counted floating traffic flow data of each road section at the observation time point.
Optionally, step C further includes:
step C1, counting the trajectory data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix, and calculating the total human activity of different activity points in each time period;
and C2, calculating the total amount of human activities in each grid in the traffic road section according to the total amount of human activities in different grids in each time period.
Optionally, step D further includes:
calculating an average of a total amount of human activity within a gridESum varianceδAnd judging whether the total amount of human activities of the grid on which the transportation facility is positioned is [0, E +2 ]δ]If the number of the traffic facilities is within the preset range, judging that the traffic facilities do not belong to the traffic facilities to be improved, otherwise, judging that the traffic facilities belong to the traffic facilities to be improved.
A second embodiment of the present invention is a system for identifying transportation facilities to be improved based on spatiotemporal trajectory data, comprising:
the mobile phone comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring mobile phone signaling data and floating car data, respectively preprocessing the mobile phone signaling data and the floating car data, and generating to-be-processed signaling data and to-be-processed car data which correspond to a specific format;
the activity data extraction module is used for extracting activity points from the signaling data to be processed according to the preset rules of time and space to obtain the trajectory data of the activity points and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to the preset data analysis rules;
the measurement index acquisition module is used for acquiring a traffic facility measurement index according to the moving point track data and the traffic facility flow space-time matrix;
and the identification comparison module is used for obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes and identifying the traffic facilities to be improved.
Optionally, the activity data extracting module includes:
the vehicle data dividing unit is used for dividing the vehicle data to be processed into at least two characteristic day data according to the acquisition time of the floating vehicle data, dividing each characteristic day data into a plurality of time periods, and taking each time period as an observation time point;
and the flow matrix construction unit is used for constructing a traffic facility flow space-time matrix according to the counted floating vehicle flow data of each road section at the observation time point.
Optionally, the metric obtaining module includes:
the time interval activity total amount calculating unit is used for counting the track data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix and calculating the human activity total amount of different activity points in each time interval;
and the grid activity total amount calculating unit is used for calculating the human activity total amount in each grid in the traffic road section according to the human activity total amount in different grids in each time period.
Optionally, the identification and alignment module includes:
a threshold comparison unit for calculating the average value of the total human activities in the gridESum varianceδAnd judging whether the total amount of human activities of the grid on which the transportation facility is positioned is [0, E +2 ]δ]If the number of the traffic facilities is within the preset range, judging that the traffic facilities do not belong to the traffic facilities to be improved, otherwise, judging that the traffic facilities belong to the traffic facilities to be improved.
The method and the system for identifying the traffic facilities to be improved based on the space-time trajectory data have the advantages that the multisource space-time trajectory data such as mobile phone signaling data, vehicle GPS data and the like are utilized, the traffic facility utilization measurement index is established according to the extracted space-time law of group activities and travel, the adaptability of the group activities and the traffic facilities is quantitatively evaluated, and the traffic facilities to be improved are identified.
Drawings
FIG. 1 is a flow chart illustrating the steps of a method for identifying transportation facilities to be improved based on spatiotemporal trajectory data according to the present invention;
FIG. 2 is a schematic structural diagram of a traffic facility identification method to be improved according to the present invention;
FIG. 3 is a block diagram of a schematic structure of a transportation facility identification system to be improved based on space-time trajectory data according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The first embodiment of the invention provides a method for identifying a to-be-improved transportation facility based on space-time trajectory data, as shown in fig. 1, comprising the following steps:
and S1, acquiring the mobile phone signaling data and the floating car data, and respectively preprocessing the mobile phone signaling data and the floating car data to generate the signaling data to be processed and the car data to be processed which correspond to the specific format.
The server background acquires mobile phone signaling data and receives floating car data acquired by a floating car GPS positioning module, and the acquired mobile phone signaling data and the floating car data are data generated by people in a certain area within a certain time, so that the data need to be preprocessed, and the to-be-processed signaling data and the to-be-processed car data meeting specific formats are obtained.
In a further embodiment, step S100 specifically includes:
step S101, acquiring mobile phone signaling data, performing quality cleaning on the original mobile phone signaling data, removing repeated data, removing data with missing attributes, removing data with time and space not within a preset range, removing user data with the number of user points smaller than or larger than a certain threshold value, and generating preprocessed signaling data;
and S102, performing quality cleaning on the floating car data, removing repeated data, removing data with missing attributes, removing data with space-time and space not within a preset range, and performing mean value completion according to sampling frequency and adjacent sampling data to obtain preprocessed car data.
Step S103, converting the spatial resolution of the preprocessed signaling data according to the resolution of the preset regular grid scale to obtain the signaling data to be processed sampled based on the preset regular grid scale;
and S104, removing data deletion which is not in the preset sampling frequency range in the preprocessed vehicle data, and converting the preprocessed vehicle data into the data of the vehicle to be processed which is sampled at equal time intervals according to the preset frequency.
In specific implementation, the mobile phone signaling data and floating car data are preprocessed to obtain data which meets the post-processing requirements, and the specific content comprises the following steps:
performing quality cleaning on the mobile phone signaling data, including removing repeated data, removing data with lost attributes, removing data with time and space out of a research range, and removing user data with the number of user points smaller than or larger than a certain threshold; the threshold value is chosen depending on the specific data type, data format, and data quality. Preferably, the threshold value ranges from less than 3 days to more than 100 days.
Performing quality cleaning on floating car data, including removing repeated data, removing data with missing attributes, and removing data with time and space out of the research range; and for the data with broken chains, performing mean value compensation according to the sampling frequency and the adjacent sampling data.
For multi-source spatio-temporal trajectory data, the influence of spatial resolution is considered. And uniformly converting the spatial resolution of the mobile phone signaling data into a scale based on a regular grid. The scale size of a regular grid is typically dependent on the spatial resolution of the two types of data themselves. The grid is a plurality of active area blocks which are divided from the active area of the population according to a preset scale, and the preferred scale is 500m by 500 m.
For multi-source space-time trajectory data, the influence of time resolution is considered, data with too sparse frequency is removed aiming at the condition that the floating car data sampling frequency is different, and the data meeting the frequency requirement is uniformly converted into data sampled at equal time intervals.
And step S2, extracting the active points from the signaling data to be processed according to the preset time and space rules to obtain the active point track data, and obtaining the traffic facility flow space-time matrix from the vehicle data to be processed according to the preset data analysis rules.
According to the rule of setting time and space, the active point is extracted from the signaling data to be processed acquired in the step S1, and active point trajectory data is obtained.
Specifically, the activities of the crowd in the grid are counted in time or space, and whether the traffic facilities in the grid need to be perfected or not is analyzed and judged.
Preferably, the step S2 of extracting the active point from the signaling data to be processed according to the preset time and space rules to obtain the active point trajectory data further includes:
s211, sequencing the signaling data to be processed according to a preset sequencing rule to obtain an individual time sequence track;
step S212, calculating the time for entering and leaving each grid according to the individual time sequence track, and setting a first position point where the individual enters as a first active point in the active point track;
step S213, calculating the space distance and the time difference between each position point in the individual time sequence track and the existing active point, if the space distance is smaller than a set threshold and the time difference is smaller than a first threshold, adding the position point into the active point, otherwise, setting the position point as a new active point until all the position points in the time sequence track are completely calculated, and obtaining a candidate active point track;
step S214, candidate active points in the candidate active point track are obtained, and when the difference value between the entering time and the leaving time of the candidate active points is smaller than a second set threshold value, the corresponding candidate active points are removed from the candidate active point track, and active point track data are generated.
In specific implementation, the motion point track of the person is obtained by extracting the motion point of the person from the processed mobile phone signaling data. The method for extracting the active points is mainly judged by setting time and space rules, and the specific method is as follows:
sequencing the generated mobile phone signaling data according to people and time to obtain individual time sequence tracks of the people;
calculating the time of the individual entering and leaving each position (grid) by utilizing the individual time sequence track, wherein the first position is set as a first active point in the active point track;
calculating the space distance and time difference value between each point in the individual time sequence track and the active point in the existing active point track along with the time movement; if the spatial distance is smaller than a first threshold value and the time difference value is smaller than a second threshold value, adding the point to the active point; otherwise, the point is set as a new active point; until all position points in the time sequence track are completely calculated, obtaining a candidate moving point track; the first threshold value is preferably set in the range of 500m to 1000 m.
And regarding candidate active points in the candidate active point tracks, if the difference value of the entry time and the exit time of the point is less than a second threshold value, determining that the position point is not an active point, removing the position point from the candidate active point tracks, and finally obtaining the active point tracks. Preferably, the second threshold value ranges from 1 hour to 3 hours.
Further, the step S2, according to a preset data analysis rule, obtaining a transportation facility flow space-time matrix from the vehicle data to be processed includes:
step S221, dividing the data of the vehicle to be processed into at least two characteristic day data according to the acquisition time of the floating vehicle data, dividing each characteristic day data into a plurality of time periods, and taking each time period as an observation time point;
and step S222, constructing a traffic facility flow space-time matrix according to the counted floating traffic flow data of each road section at the observation time point.
The floating car data processed in the above step S1 is used to calculate the actual flow rate through the transportation facility. The specific method comprises the following steps:
according to the acquisition time of the floating car data, the study data is divided into two characteristic days of the week and the weekend, and the data of each characteristic day is divided into a plurality of periods (24 hours). During research, three moments of 8:30, 12:30 and 18:30 are selected as observation time points according to the change trend of the peak in the morning and at the evening.
The method for constructing the traffic facility flow space-time matrix specifically comprises the following steps: and obtaining a traffic facility traffic space-time matrix according to the traffic data of a certain road section at a certain observation time point through statistics, and taking the traffic space-time matrix as a reference for judging the traffic jam condition. Is shown as
Where i represents the identification number of the link and t represents time. The meaning of the traffic facility flow space-time matrix value is the real traffic flow number passing through a certain road section in a certain time period.
And step S3, obtaining a traffic facility utilization measurement index according to the moving point trajectory data and the traffic facility flow space-time matrix.
In this step, the measurement index is calculated according to the trajectory data of the active points and the traffic facility flow space-time matrix calculated in the step S2.
In a specific embodiment, the step includes:
step S31, counting the trajectory data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix, and calculating the total human activity of different activity points in each time interval;
and step S32, calculating the total amount of human activities in each grid in the traffic road section according to the total amount of human activities in different grids in each time period.
And establishing a traffic facility utilization measurement index according to the group activity-time-out law by using the activity point track data obtained in the steps. The specific method comprises the following steps:
and counting the acquired activity tracks according to the grid numbers and the time consistent with the set traffic facility flow space-time matrix, and calculating the total human activity in different grids at each time interval. Is expressed as [, ]
Where j denotes the grid number and t denotes time.
And calculating the total activity of the grid where the traffic road section is located. If the segment spans multiple grids, then the total amount of activity for the multiple grids is averaged. Is shown as
。
And step S4, obtaining the adaptability between the group activity flow and the transportation facilities according to the transportation facility utilization measurement indexes, and identifying the transportation facilities to be improved.
In this step, it is determined whether the transportation device in the grid needs to be improved according to the transportation utilization metric calculated in step S3, in a specific embodiment, the step S4 further includes:
mean value for calculating total amount of human activity in gridESum varianceδAnd judging the person of the grid where the traffic facilities are locatedWhether the total amount of class activity is [0, E +2 ]δ]If the number of the traffic facilities is within the preset range, judging that the traffic facilities do not belong to the traffic facilities to be improved, otherwise, judging that the traffic facilities belong to the traffic facilities to be improved.
In specific implementation, the group activity flow in the specific time frame is obtained in the step
Calculating an average of the total amount of human activity within a particular time frameESum varianceδAnd determining the total amount of human activity
Whether or not it is [0, E +2 ]δ]If the current grid is in the improved state, the adaptability of the traffic facility in the current grid in the time interval is sufficient and does not belong to the traffic facility to be improved, otherwise, the adaptability of the traffic facility in the time interval is considered to be insufficient and belongs to the traffic facility to be improved.
With reference to fig. 2, the method disclosed by the present invention respectively preprocesses the mobile phone signaling data to obtain the activity track of the crowd and preprocesses the floating car data to obtain the traffic facility flow matrix, combines the activity track and the traffic facility flow matrix, and proposes to establish the traffic facility utilization metric index according to the extracted space-time distribution of the group activities and the transformation rule thereof, so as to realize the group activities and the traffic facility adaptability evaluation and identify the traffic facility to be improved. The invention provides a new method for evaluating traffic facilities driven by multi-source space-time trajectory data and identifying the traffic facilities to be improved, thereby realizing refined urban traffic management.
The invention breaks through the fact that the traditional method can not realize the empirical evaluation of the real activity utilization of the traffic facilities, realizes the traffic jam analysis and relief driven by the supporting data, and realizes the scientific decision of the refined urban traffic planning and the intelligent urban traffic management.
A second embodiment of the present invention is a system 30 for identifying transportation facilities to be improved based on spatiotemporal trajectory data, as shown in fig. 3, comprising:
the preprocessing module 310 is configured to acquire mobile phone signaling data and floating car data, and preprocess the mobile phone signaling data and the floating car data respectively to generate to-be-processed signaling data and to-be-processed car data corresponding to a specific format; the function of which is as described in step S1.
The activity data extraction module 320 is used for extracting activity points from the signaling data to be processed according to the preset rules of time and space to obtain the trajectory data of the activity points, and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to the preset data analysis rules; the function of which is as described in step S2.
The measurement index acquisition module 330 is configured to obtain a traffic facility measurement index according to the activity point trajectory data and the traffic facility flow spatio-temporal matrix; the function of which is as described in step S3.
The identifying and comparing module 340 is configured to obtain adaptability between the group activity traffic and the transportation according to the transportation utilization measure, and identify the transportation to be improved, where the function of the identifying and comparing module is as described in step S4.
Optionally, the activity data extracting module 320 includes:
and the vehicle data dividing unit is used for dividing the vehicle data to be processed into at least two characteristic day data according to the acquisition time of the floating vehicle data, dividing each characteristic day data into a plurality of time periods, and taking each time period as an observation time point.
And the flow matrix construction unit is used for constructing a traffic facility flow space-time matrix according to the counted floating vehicle flow data of each road section at the observation time point.
Optionally, the metric index obtaining module 330 includes:
the time interval activity total amount calculating unit is used for counting the track data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix and calculating the human activity total amount of different activity points in each time interval;
and the grid activity total amount calculating unit is used for calculating the human activity total amount in each grid in the traffic road section according to the human activity total amount in different grids in each time period.
Optionally, the identification and alignment module 340 includes:
a threshold comparison unit for calculating the average value of the total human activities in the gridESum varianceδAnd judging whether the total amount of human activities of the grid on which the transportation facility is positioned is [0, E +2 ]δ]If the number of the traffic facilities is within the preset range, judging that the traffic facilities do not belong to the traffic facilities to be improved, otherwise, judging that the traffic facilities belong to the traffic facilities to be improved.
The invention provides a method and a system for identifying traffic facilities to be improved based on space-time trajectory data, which are used for acquiring mobile phone signaling data and floating car data, respectively preprocessing the mobile phone signaling data and the floating car data, and generating signaling data to be processed and car data to be processed; extracting active points from signaling data to be processed to obtain active point track data, and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to a preset data analysis rule to finally obtain a traffic facility utilization measurement index; and obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes, and identifying the traffic facilities to be improved. The method and the system of the invention utilize the multisource space-time trajectory data such as the mobile phone signaling data, the vehicle GPS data and the like to establish the traffic facility utilization measurement index, quantitatively evaluate the adaptability of group activities and traffic facilities and identify the traffic facilities to be improved.
It should be understood that equivalents and modifications of the technical solution and inventive concept thereof may occur to those skilled in the art, and all such modifications and alterations should fall within the scope of the appended claims.
Claims (10)
1. A method for identifying a to-be-improved traffic facility based on space-time trajectory data is characterized by comprising the following steps:
step A, acquiring mobile phone signaling data and floating car data, and respectively preprocessing the mobile phone signaling data and the floating car data to generate to-be-processed signaling data and to-be-processed car data which correspond to a specific format;
b, extracting active points from the signaling data to be processed according to preset time and space rules to obtain active point track data, and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to preset data analysis rules;
step C, obtaining a traffic facility utilization measurement index according to the moving point track data and the traffic facility flow space-time matrix;
and D, obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes, identifying the traffic facilities to be improved and outputting the traffic facilities.
2. The method for identifying transportation facilities to be improved based on spatiotemporal trajectory data as claimed in claim 1, wherein the step of preprocessing the cell phone signaling data and floating car data in the step A comprises:
step A1, performing quality cleaning on the mobile phone signaling data, removing repeated data, removing data with missing attributes, removing data with space time and space not in a preset range, and removing user data with user point quantity smaller than or larger than a certain threshold value to obtain preprocessed signaling data;
a2, performing quality cleaning on floating car data, removing repeated data, removing data with missing attributes, removing data with space and time not within a preset range, and performing mean value completion according to sampling frequency and adjacent sampling data to obtain preprocessed car data;
step A3, converting the spatial resolution of the preprocessed signaling data according to the resolution of the preset regular grid scale to obtain the signaling data to be processed sampled based on the preset regular grid scale;
and A4, removing data deletion which is not in the preset sampling frequency range in the preprocessed vehicle data, and converting the preprocessed vehicle data into the vehicle data to be processed sampled at equal time intervals according to the preset frequency.
3. The method for identifying transportation facilities to be improved based on spatiotemporal trajectory data as claimed in claim 2, wherein the step B of extracting the active points from the signaling data to be processed according to the rules of preset time and space to obtain the trajectory data of the active points further comprises:
b11, sequencing the signaling data to be processed according to a preset sequencing rule to obtain an individual time sequence track;
step B12, calculating the time of entering and leaving each grid according to the individual time sequence track, and setting the first position point of the individual entering as the first active point in the active point track;
step B13, calculating the space distance and the time difference value between each position point in the individual time sequence track and the existing active point, if the space distance is smaller than a set threshold value and the time difference value is smaller than a first threshold value, adding the position point into the active point, otherwise, setting the position point as a new active point until all the position points in the individual time sequence track are completely calculated, and obtaining a candidate active point track;
and step B14, acquiring candidate active points in the candidate active point track, and when detecting that the difference value between the entering time and the leaving time of the candidate active points is smaller than a second set threshold, removing the corresponding candidate active points from the candidate active point track to generate active point track data.
4. The method for identifying transportation facilities to be improved based on spatiotemporal trajectory data as claimed in claim 2, wherein the step of obtaining the transportation facility flow spatiotemporal matrix from the vehicle data to be processed according to the preset data analysis rule comprises:
step B21, dividing the data of the vehicle to be processed into at least two characteristic day data according to the acquisition time of the data of the floating vehicle, dividing each characteristic day data into a plurality of time intervals, and taking each time interval as an observation time point;
and B22, constructing a traffic facility flow space-time matrix according to the counted floating traffic flow data of each road section at the observation time point.
5. The spatiotemporal trajectory data-based transportation facility identification method to be improved according to claim 4, wherein the step C further comprises:
step C1, counting the trajectory data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix, and calculating the total human activity of different activity points in each time period;
and C2, calculating the total amount of human activities in each grid in the traffic road section according to the total amount of human activities in different grids in each time period.
6. The spatiotemporal trajectory data-based transportation facility identification method to be improved according to claim 4, wherein the step D further comprises:
calculating the mean E and the variance delta of the total amount of human activities in the grid;
and judging whether the total human activity of the grid in which the traffic facilities are located is between [0, E +2 delta ], if so, judging that the traffic facilities do not belong to the traffic facilities to be improved, otherwise, judging that the traffic facilities belong to the traffic facilities to be improved.
7. A system for identifying a transportation facility to be improved based on spatiotemporal trajectory data, comprising:
the mobile phone comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for acquiring mobile phone signaling data and floating car data, respectively preprocessing the mobile phone signaling data and the floating car data, and generating to-be-processed signaling data and to-be-processed car data which correspond to a specific format;
the activity data extraction module is used for extracting activity points from the signaling data to be processed according to the preset rules of time and space to obtain the trajectory data of the activity points and obtaining a traffic facility flow space-time matrix from the vehicle data to be processed according to the preset data analysis rules;
the measurement index acquisition module is used for acquiring a traffic facility utilization measurement index according to the moving point track data and the traffic facility flow space-time matrix;
and the identification comparison module is used for obtaining the adaptability between the group activity flow and the traffic facilities according to the traffic facility utilization measurement indexes, identifying the traffic facilities to be improved and outputting the traffic facilities.
8. The spatiotemporal trajectory data-based transportation facility identification system to be improved system of claim 7, wherein the activity data extraction module comprises:
the vehicle data dividing unit is used for dividing the vehicle data to be processed into at least two characteristic day data according to the acquisition time of the floating vehicle data, dividing each characteristic day data into a plurality of time periods, and taking each time period as an observation time point;
and the flow matrix construction unit is used for constructing a traffic facility flow space-time matrix according to the counted floating vehicle flow data of each road section at the observation time point.
9. The system for identifying transportation facilities to be improved based on spatiotemporal trajectory data as claimed in claim 7, wherein the metric obtaining module comprises:
the time interval activity total amount calculating unit is used for counting the track data of the activity points according to the grid numbers and the time consistent with the traffic facility flow space-time matrix and calculating the human activity total amount of different activity points in each time interval;
and the grid activity total amount calculating unit is used for calculating the human activity total amount in each grid in the traffic road section according to the human activity total amount in different grids in each time period.
10. The system for identifying transportation facilities to be improved based on spatiotemporal trajectory data as claimed in claim 7, wherein the identification comparison module comprises:
and the threshold comparison unit is used for calculating the mean E and the variance delta of the total human activities in the grid and judging whether the total human activities of the grid in which the transportation facilities are located are between [0, E +2 delta ], if so, judging that the transportation facilities do not belong to the transportation facilities to be improved, otherwise, judging that the transportation facilities belong to the transportation facilities to be improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810410574.4A CN108597224B (en) | 2018-05-02 | 2018-05-02 | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810410574.4A CN108597224B (en) | 2018-05-02 | 2018-05-02 | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108597224A CN108597224A (en) | 2018-09-28 |
| CN108597224B true CN108597224B (en) | 2020-05-19 |
Family
ID=63619608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810410574.4A Active CN108597224B (en) | 2018-05-02 | 2018-05-02 | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108597224B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113009532A (en) * | 2021-04-01 | 2021-06-22 | 南京理工大学 | Moving track data completion method |
| CN114386529B (en) * | 2022-01-19 | 2023-04-07 | 北京融信数联科技有限公司 | Community service analysis method and system based on big data and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000322402A (en) * | 1999-05-11 | 2000-11-24 | Hitachi Ltd | Stream of people analyzing method |
| CN101976500A (en) * | 2010-10-25 | 2011-02-16 | 中国科学院深圳先进技术研究院 | Method and system for analyzing traffic network |
| CN104200667A (en) * | 2014-09-19 | 2014-12-10 | 上海美慧软件有限公司 | Traffic jam grade detection method based on cellphone signal data |
| CN106211071A (en) * | 2016-07-04 | 2016-12-07 | 深圳大学 | Group activity method of data capture based on multi-source space-time trajectory data and system |
| CN107230350A (en) * | 2017-06-23 | 2017-10-03 | 东南大学 | A kind of urban transportation amount acquisition methods based on bayonet socket Yu mobile phone flow call bill data |
-
2018
- 2018-05-02 CN CN201810410574.4A patent/CN108597224B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000322402A (en) * | 1999-05-11 | 2000-11-24 | Hitachi Ltd | Stream of people analyzing method |
| CN101976500A (en) * | 2010-10-25 | 2011-02-16 | 中国科学院深圳先进技术研究院 | Method and system for analyzing traffic network |
| CN104200667A (en) * | 2014-09-19 | 2014-12-10 | 上海美慧软件有限公司 | Traffic jam grade detection method based on cellphone signal data |
| CN106211071A (en) * | 2016-07-04 | 2016-12-07 | 深圳大学 | Group activity method of data capture based on multi-source space-time trajectory data and system |
| CN107230350A (en) * | 2017-06-23 | 2017-10-03 | 东南大学 | A kind of urban transportation amount acquisition methods based on bayonet socket Yu mobile phone flow call bill data |
Non-Patent Citations (1)
| Title |
|---|
| 面向智慧城市的公共服务设施建设决策研究;陈恺文;《中国优秀硕士学位论文全文数据库经济与管理科学辑》;20170315;J155-81 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108597224A (en) | 2018-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871876B (en) | Expressway road condition identification and prediction method based on floating car data | |
| CN107610469A (en) | A kind of day dimension regional traffic index forecasting method for considering multifactor impact | |
| CN107977673B (en) | Economic activity population identification method based on big data | |
| CN110390349A (en) | Bus passenger flow volume based on XGBoost model predicts modeling method | |
| CN108647743B (en) | Driver safety portrait system | |
| CN108648445B (en) | Dynamic traffic situation prediction method based on traffic big data | |
| CN110516866B (en) | Real-time estimation method for urban rail transit train crowding degree | |
| Feng et al. | Towards big data analytics and mining for UK traffic accident analysis, visualization & prediction | |
| CN108597224B (en) | Method and system for identifying to-be-improved traffic facilities based on space-time trajectory data | |
| CN107766636A (en) | A kind of urban intersection safe evaluation method based on extreme value theory and microscopic simulation | |
| CN110889092A (en) | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data | |
| CN107992958A (en) | Population super-limit prewarning method based on ARMA | |
| Yao et al. | Understanding vehicles commuting pattern based on license plate recognition data | |
| CN111598333A (en) | Passenger flow data prediction method and device | |
| CN114596700A (en) | Real-time highway section flow estimation method based on portal data | |
| CN115995149A (en) | Multi-source data-based parking supply and demand characteristic dynamic evaluation method and system | |
| CN113112076B (en) | Passenger flow distribution mode discovery and prediction method | |
| Hong et al. | Conserved quantities in human mobility: From locations to trips | |
| CN116168356B (en) | Vehicle damage judging method based on computer vision | |
| CN109523788B (en) | Road section operation effect evaluation method | |
| CN111680888A (en) | Method for determining road network capacity based on RFID data | |
| CN113822367B (en) | Regional behavior analysis method, system and medium based on human face | |
| CN113516850B (en) | Pipeline traffic flow data acquisition method based on space syntactic analysis | |
| CN112309129B (en) | OD matrix forming method for vehicle travel characteristic classification based on checkpoint license plate recognition | |
| CN112597264B (en) | River patrol trajectory concentration degree analysis method based on space-time big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |