CN112133090A - Multi-mode traffic distribution model construction method based on mobile phone signaling data - Google Patents
Multi-mode traffic distribution model construction method based on mobile phone signaling data Download PDFInfo
- Publication number
- CN112133090A CN112133090A CN202010980271.3A CN202010980271A CN112133090A CN 112133090 A CN112133090 A CN 112133090A CN 202010980271 A CN202010980271 A CN 202010980271A CN 112133090 A CN112133090 A CN 112133090A
- Authority
- CN
- China
- Prior art keywords
- traffic
- travel
- mobile phone
- mode
- data
- 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.)
- Pending
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
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
Abstract
The invention discloses a multi-mode traffic distribution model construction method based on mobile phone signaling data. And then carrying out rule matching on the resident trip survey data and the mobile phone signaling data to obtain mobile phone signaling track data with a traffic mode label. And multi-source data are fused to extract characteristic parameters, the characteristic parameters are screened by chi-square test, a traffic mode division model is constructed by applying a random forest classification algorithm, and full-sample division mode travel OD estimation is completed by sample expansion. The influence of land layout and traffic modes on traffic distribution is quantified, a multi-mode traffic distribution model is built based on a gravity model, model parameter calibration is completed by utilizing a full-sample separation mode travel OD, and finally multi-mode traffic distribution prediction work is completed.
Description
Technical Field
The invention relates to the technical field of electronics and the field of communication, in particular to a multi-mode traffic distribution model construction method based on mobile phone signaling data.
Background
In recent years, with the rapid development of information technology, a mobile phone has rapidly become popular in the country as a communication device that is convenient to carry. The enormous mobile phone users and the data transmission amount bring about nearly full sample of demographic observation data. In the using process, the mobile phone terminal establishes contact with the adjacent cellular base station in order to meet the requirements of user communication and internet access, and at the moment, the time when the user accesses the base station and the position information of the base station are recorded to generate mobile phone signaling data. The system can track individuals in real time and provide user positions, and provides a new idea for collection of travel information.
Although the mobile phone signaling data has many advantages over the traditional traffic data and is applied to many urban traffic planning and traffic information systems, the mobile phone signaling data is difficult to be sufficiently mined. In addition, it is a current research difficulty to improve the traditional traffic model by using the existing big data. The traditional traffic model is constructed based on traditional resident survey data, and big data such as mobile phone signaling data are not specially provided for the traffic model, so how to fuse the big data and the traditional traffic model is a key technology and research focus which needs to be solved urgently at present.
Disclosure of Invention
The invention provides a multi-mode traffic distribution model construction method based on mobile phone signaling data, aiming at solving the problems in the background technology.
The technical scheme is as follows:
a multi-mode traffic distribution model construction method based on mobile phone signaling data comprises the following steps:
(1) identifying travel stopping points by using a space-time clustering algorithm according to the time-space characteristics of the base station track points, and extracting travel chain information so as to be matched with an actual road network;
(2) matching a base station in a trip chain with an intersection in a road network by a probability decision method, and acquiring trip track information of a mobile phone user in the urban road network for matching with resident trip survey data;
(3) matching resident trip survey data with trip track information in a road network by using a rule matching method, and acquiring mobile phone signaling track data with a traffic mode label as a sample space;
(4) screening characteristic parameters based on chi-square test, constructing a traffic mode division model by using a random forest classification algorithm, converting a base station OD into a travel OD between traffic cells, and finishing the estimation of the full-sample split mode travel OD through sample expansion;
(5) constructing a multi-mode traffic distribution model by using a gravity model according to the intrinsic influence of the land layout and the traffic mode on traffic distribution;
(6) and completing model parameter calibration work by using the acquired full sample sub-mode travel OD, and completing model construction.
Preferably: the process of the step (1) comprises the following steps:
s1, acquiring base station position information corresponding to the mobile phone signaling data, and sorting all base station position information in one day according to a time sequence to extract the approximate activity position information of the user in the day;
s2, setting time, distance and speed threshold values according to a space-time clustering algorithm;
s3, dividing the track points into determined stop points, possible stop points and displacement points by using time and speed threshold parameters;
s4, performing secondary judgment on the possible stop points by using the distance threshold parameters, and finally obtaining all the determined stop points in the track points to obtain the trip chain information.
Preferably: the process of the step (2) comprises the following steps:
s1, generating a base station coverage range through an ArcGIS neighborhood analysis tool, and then obtaining an intersection-to-road correspondence table, a base station-to-intersection correspondence table and a base station coverage range-in-road correspondence table through a spatial connection tool;
s2, numbering each travel base station track sequence, and assuming a set Si={j1,j2,…,jnDenotes a track, where jiIndicating base stations occupied in the trajectory;
s3 accumulating trace S according to the base station road corresponding tableiIn each base station jiCovered road, obtaining the railRoad frequency table for track coveragei;
S4 for each base station jiAnd extracting intersections in the coverage range and a road set R consisting of corresponding intersections according to the correspondence table of the base stations and the intersectionsi;
S5 frequency table F obtained according to statisticsiDenotes RiRoad with second highest intermediate frequencyAnd screening the intersection consisting of the roads, and when the intersection isThen delete the base station ji;
S6, calculating the distance D between the intersection screened in the previous step and the base station, and corresponding the base station to the road network intersection according to the minimum distance principle;
s7 circularly matching all base stations in the track sequence to obtain an intersection sequence CiFor non-adjacent intersections, calling a shortest path function to connect the intersections to obtain an intersection sequence which is completely connected on a road network;
s8 circulation judgment intersection sequence CiThree adjacent middle data C(i-1),Ci,C(i+1)Whether the data is A-B-A type data or not, if so, deleting the intersection Ci,C(i+1);
S9, connecting adjacent intersections to obtain track data of the users on the road network, namely travel track information of the mobile phone users in the urban road network, and matching the travel track information with resident travel survey data.
Preferably: the process of the step (3) comprises the following steps:
s1, acquiring gender and age of residents, the number of a departure traffic cell, the number of an arrival traffic cell, departure time and arrival time of each travel record through resident travel survey;
s2, matching the date of resident travel survey data, the departure traffic cell and the arrival traffic cell with travel track information extracted from the mobile phone signaling data, and performing primary screening;
s3, carrying out secondary screening on the mobile phone data track information according to the departure time of each resident trip survey data;
s4, performing final matching according to the gender and the age attribute, and if the matching is successful, defining the travel mode of the resident travel survey data as the travel mode corresponding to the travel track of a certain mobile phone, namely obtaining the mobile phone signaling track data with the traffic mode label.
Preferably: the process of the step (4) comprises the following steps:
s1, fusing the mobile phone signaling data and the GPS navigation data, and extracting characteristic parameters according to the track spatio-temporal characteristics and the path navigation characteristics respectively;
s2, screening the optimal model precision under each characteristic dimension by using a Chi-square test method, namely screening by observing the deviation between an actual value and a theoretical value, wherein the test formula is as follows:
in the formula: chi2Denotes the deviation, E is the theoretical value, xiIs a sample observed value, and n is the total number of the characteristic parameters; selecting the number of the features corresponding to the highest precision;
s3, obtaining the importance of each characteristic parameter according to the following formula, analyzing the importance of the characteristic parameters, and constructing a traffic mode division model according to a random forest algorithm;
in the formula: g(p)For the importance of the characteristic parameter, K is the number of classes, pkIs the probability that the sample point belongs to the kth class;
s4, matching the base station and the traffic cell by using a traditional traffic cell division method, mainly taking administrative boundaries, using natural obstacles in the administrative district as a main division basis, adopting a surface-to-surface, point-to-surface or point-to-point matching method, and converting the base station OD into a travel OD between the traffic cells;
s5, considering the market share proportion of mobile phone operation and the popularity of mobile phones, completing sample expansion from mobile phones to mobile phone users, sample expansion from single operator to all operators, sample expansion from all mobile phone users to all travel residents, and obtaining the sub-mode OD estimation of the whole sample.
Preferably: the process of the step (5) comprises the following steps:
s1, establishing a relation between the land with different land properties and the district traffic volume, and obtaining unit land occurrence attraction rates of various land properties through fitting;
s2, taking the travel distance as traffic impedance, extracting travel distances and travel times of different traffic modes between the same origin-destination point from the Goods API as reference factors, and respectively considering generalized cost functions of walking, bicycles, electric vehicles, buses and cars;
s3, under the condition of considering land layout influence factors, carrying out logarithmic processing on the gravity model basic model, and obtaining the cell attraction amount according to the traffic attraction rate of various land properties and the land area of corresponding properties to obtain a model formula:
ln(Tij)=α ln(Ri(u))+β ln(Rj(u))+γ ln(Cij)+k
in the formula: t isijThe traffic volume of the traffic cell i and the traffic cell j is obtained; ri(u) traffic occurrence of the departure cell i; rj(u) is the amount of traffic attraction to cell j; cijThe trip impedances of the traffic cell i and the traffic cell j are shown; alpha, beta, gamma and k are undetermined coefficients;
s4 trip impedance CijThe model formula under different modes of transportation is as follows:
utility function of walking:
Fw=ω1lw+θ1tw
in the formula: lwRepresenting a walking travel distance; t is twRepresenting a walking travel time; omega1、θ1Are all undetermined parameters。
Utility function of bicycle:
Fb=ω2lb+θ2(tb+2)
in the formula: lbRepresenting the travel distance of the bicycle; t is tbRepresenting the travel time of the bicycle; omega2、θ2Are all undetermined parameters; 2 is defined as the parking time 2 min;
utility function of electric vehicle:
Fe=ω3le+θ3(te+2)
in the formula: leRepresenting the travel distance of the electric vehicle; t is teRepresenting the travel time of the electric vehicle; omega3、θ3Are all undetermined parameters; 2 is defined as the parking time 2 min;
utility function of bus:
Fp=ω4lp+θ4tp+θ5fp
in the formula: lpRepresenting the travel distance of the bus; t is tpRepresenting the travel time of the bus; f. ofpRepresents bus ticket cost; omega4、θ4、θ5Are all undetermined parameters;
utility function of car:
Fc=ω6lc+θ6tc+θ7fc
in the formula: lcRepresenting the travel distance of the car; t is tcRepresenting the car travel time; f. ofcRepresenting the parking cost of the car; omega6、θ6、θ7Are all undetermined parameters.
Preferably: the process of the step (6) comprises the following steps:
s1, dividing land according to the land property classification standard, connecting the land property map layer with the control gauge unit map layer by using GIS software, numbering, and calculating the area of various land properties;
s2, assuming the starting point and the ending point of travel as the gravity center of the traffic districts, acquiring the longitude and latitude of each traffic district, and crawling various traffic expenses among the traffic districts from the API of the Gagde map by using python;
s3, carrying out fitting analysis on the traffic volume and the attraction volume of the traffic cell and various land characteristics of the traffic cell to obtain the travel rate of the land characteristics of various types, and summarizing and obtaining a traffic distribution model parameter selection table of each traffic mode;
and S4, combining the obtained full-sample mode travel OD information, fitting a corresponding traffic distribution model according to a parameter selection table, and obtaining traffic distribution model formulas of various traffic modes.
The invention has the advantages of
1. In the aspect of travel characteristic analysis of mobile phone signaling data:
the mobile phone signaling data has many inherent defects of data attributes (such as sampling deviation, noise and the like) in the collection process; different from traditional resident trip survey data, the mobile phone signaling data lack some attributes, such as social statistics attributes of population, trip purpose, trip mode and other trip characteristics; the number of the mobile phone signaling data is large, the variety is various, and the mining degree of the existing theory and technology to the mobile phone signaling data is limited. The application rule matching method is innovative, and the actual resident travel survey data and the mobile phone signaling data are well matched to obtain the mobile phone signaling track data with the traffic travel mode label.
2. In the aspect of traffic mode division:
at present, methods for mining travel modes from trajectory data at home and abroad are mainly classified into three categories, including traffic mode division based on rule inspiration, traffic mode division based on probability statistics and traffic mode division based on machine learning. Compared with the existing three traffic mode division methods, the rule heuristic based method at least requires that the detected traffic mode has prior knowledge to construct a rule set division traffic mode; the method based on probability statistics is used for carrying out abstract transformation on prior knowledge and is suitable for distinguishing methods with obviously different characteristic variables; machine learning based methods are classified into unsupervised and supervised, with the difference being whether tagged data is used in the modeling training. At present, a supervised machine learning method is more widely applied, but a large amount of sample data with labels cannot be obtained by utilizing mobile phone signaling data, and extracted characteristic variables are only limited in the aspect of travel characteristics, so that the mode identification precision is unsatisfactory. According to the invention, firstly, model data with a label is obtained, comprehensive characteristic variables are extracted, then, a random forest algorithm is applied to traffic mode division in a sample data space with the label, according to example analysis, the model precision is higher, and the overall precision reaches 90.2%.
3. In terms of traffic distribution models:
the research on traffic distribution models at home and abroad is not exhaustive, but the classical traffic distribution models have more or less various problems and can be summarized into the following three points: (1) the method is characterized in that the traffic volume between cells in traffic distribution is determined to be related to a plurality of factors of traffic modes and land layouts, but a traditional model is only measured by an adjusting coefficient k and has no meaning; (2) the impedance matrix between cells is closely related to the travel OD generated by traffic distribution, and the traditional model is only replaced by travel time or travel distance, which causes many errors. (3) The largest error is the estimation of the round trip time of the interviewee in the resident trip survey, and the interviewee generally cannot intentionally record the departure arrival time. The invention carefully considers the influence of traffic modes and land layout on traffic distribution, considers traffic impedance in different modes, measures traffic impedance by using a utility function, selects comprehensive model variables, constructs a multi-mode traffic distribution model, and has good fitting effect and average fitting level reaching 0.801 according to example analysis.
Drawings
FIG. 1 is an overall flow chart of the present invention
FIG. 2 is a three-dimensional display diagram of track points of the base station of the mobile phone in the embodiment
FIG. 3 is a diagram illustrating a path matching of a travel track of a user in an embodiment
FIG. 4 is a flow chart of rule matching in the embodiment
FIG. 5 is a statistical diagram of the accuracy of the optimal model under each feature dimension in the embodiment
FIG. 6 is a statistical chart of feature importance in the optimal feature space in the example
FIG. 7 is a statistical chart of traffic pattern classification results in the embodiment
FIG. 8 is a view of the embodiment of the trip mode of Kunshan city
FIG. 9 is a distribution diagram of the algorithm for identifying the passenger flow of the bus all day in the embodiment
FIG. 10 is a bus passage way for the year 2019 annual report all day bus in the embodiment
FIG. 11 is a diagram of the embodiment of identifying the passenger flow of cars all day
FIG. 12 is a distribution diagram of a road with a bidirectional flow rate higher than 15000 in the embodiment
FIG. 13 is a diagram showing the distribution of the properties of various plots in Kunshan city
Detailed Description
The invention is further illustrated by the following examples, without limiting the scope of the invention:
the method is characterized by identifying parking points based on a space-time clustering algorithm, extracting the travel base station track information of the user according to mobile phone signaling data, completing the matching of a base station and road network intersections in a travel chain through a probability decision method, and acquiring the travel track information of the user in the urban road network. And then carrying out rule matching on the resident trip survey data and the mobile phone signaling data to obtain mobile phone signaling track data with a traffic mode label. And multi-source data are fused to extract characteristic parameters, the characteristic parameters are screened by chi-square test, a traffic mode division model is constructed by applying a random forest classification algorithm, and full-sample division mode travel OD estimation is completed by sample expansion. The influence of land layout and traffic modes on traffic distribution is quantified, a multi-mode traffic distribution model is built based on a gravity model, model parameter calibration is completed by utilizing a full-sample separation mode travel OD, and finally multi-mode traffic distribution prediction work is completed. The whole flow chart is shown in fig. 1, and the specific content is detailed in the technical scheme, which is not described herein again.
The technical contents of the present invention will be explained below with reference to a specific example.
Combining the positioning precision of a mobile phone base station in Kun mountain city, two conditions of one trip of a mobile phone user are defined: 1) if the stay time of the user at a certain position exceeds a time threshold, the position is a stay point; 2) and the distance between the two continuous travel endpoints is more than 500m, and the signaling trigger time difference between the two points is more than 5 minutes, so that the two points form one travel. Recording all base station position information of certain user mobile phone data in one day, as shown in a three-dimensional display diagram of mobile phone base station track points in fig. 2, an X axis and a Y axis respectively represent longitude and latitude of the track points, a Z axis is a time axis, the track points are drawn according to a time sequence, all stay points are identified by using time, speed and distance thresholds, as shown by circular points, the rest are displacement points, as shown by triangles, and a user approximate travel track is obtained.
According to a path matching algorithm, a base station track sequence of mobile phone signaling data is converted into an intersection sequence in an urban road network, for example, a path matching diagram of a travel track of a certain user is shown in fig. 3, wherein a dot represents a travel track point (base station position) extracted from the mobile phone signaling data, a cross represents a corresponding intersection after matching and shortest path filling, a cross connecting line represents a real travel track of the user, and a closed line represents an inner ring overhead in a kunshan city. It can be seen that the user travels in the road network from the northwest direction to the east after going high above the bridge, and returns home after going down to the east and south at high speed. And the intersection matched with the path is basically along the cross connecting line real path.
In 2017, a large-scale comprehensive traffic survey is jointly carried out by the stock of the city of Nanjing city, the stock of the traffic planning and design research institute and the stock of the Suzhou planning and design research institute in Kunshan, 5150 households in the city centralized construction area and 250 households in the peripheral villages and towns are randomly extracted in the survey, and 38598 effective travel data are finally collected. And matching the resident trip survey data with the mobile phone signaling data rule according to the rule matching flow chart of FIG. 4.
According to the traveling structure of the Kun mountain city and the traveling characteristics of vehicles, traveling modes are divided into five types of traffic modes, namely walking, bicycles, electric vehicles, buses and cars. 5861 mobile phone travel track data are successfully matched, wherein the number of walking samples is 1656, the number of bicycle samples is 610, the number of electric car samples is 3997, the number of bus samples is 589, and the number of car samples is 2777, and the samples are used as mobile phone signaling track data sample spaces with traffic mode labels. Part of matching data is shown in the following table, id is the number of resident trip survey data, type is the category of trip modes, 1 is walking, 2 is a bicycle, 3 is a car, 4 is a bus, 5 is a car, O _ time and D _ time respectively represent departure time and arrival time filled in the survey data, O _ id and D _ id respectively represent the number of a traffic cell where a starting point and a finishing point are located, sex is the gender of the user, age is age, and leave _ time and arrival _ time respectively represent departure time and arrival time in a mobile phone trip track successfully matched.
The optimal model precision under each feature dimension is counted by using chi-square test for 20 feature parameters extracted from two aspects of travel trajectory space-time characteristics and path planning characteristics, as shown in fig. 5:
when the number of the features reaches 17, the model precision is the highest and reaches 0.902, namely the number of the features is the optimal number. Performing feature importance analysis on the optimal feature space, such as a feature importance statistical chart under the optimal feature space of fig. 6:
the random forest model construction is carried out based on the third-party module Scikit-leann (skleann) on machine learning provided in python. And randomly dividing the samples according to a ratio of 3:1 by a random function, wherein three quarters of the samples are model training samples, and the remaining quarter of the samples are test samples. In 1466 test sample sets, the number correctly identified by the random forest model reaches 1322 samples, the overall accuracy rate reaches 90.2%, and the accuracy rate of walking and cars reaches 98%. The sample model training results are shown in the following table:
according to the year report of the Ministry of industry and communications of 2020, mobile users account for approximately 70% of the total number of Kunshan mobile phone users. According to the survey data of the outgoing of the residents in 2017 of Kunshan city, the average outgoing times is about 2.82. By using mobile phone signaling data in 2019 and combining with Kun shan population calculation, the average number of trips in 2019 is 2.85. From the number of trips per capita, the OD sample expanding result is high in accuracy.
Statistical analysis is performed according to the mode division result, and the modes are shown in fig. 7. It is known from the comprehensive traffic planning of kunshan city (2017-. The traffic mode division result basically presents an accurate form, and the effectiveness of mode division is explained from the whole.
Because the map matching algorithm directly converts the base station sequence into the intersection sequence in the road network, the branch mode trip chain after sample expansion can be directly converged into the road network, and the comparison condition with real data is observed. The passenger flow distribution of buses and cars in the Kunshan network is selected for analysis, fig. 9 is a bus passenger flow distribution diagram identified by an algorithm, and fig. 10 is a full-day passenger flow corridor distribution diagram in 2019 annual reports of Kunshan city. It can be seen that the roads with bus passenger flow greater than 1500 people are basically consistent with the bus passenger flow corridors identified in the annual newspaper. Then, the all-day traffic distribution of the cars is shown in fig. 11, the analysis of the roads with the bidirectional traffic larger than 15000 is shown in fig. 12, and besides the obvious middle-loop network is identified, the major trunk roads from the major urban area to the peripheral administrative areas such as the flower bridge, the city, the jinxi and the like are also identified to have larger traffic, and accord with the basic rule of the road traffic state of the kunshan city.
According to the urban overall planning requirement of the urban planning department and the urban land classification and planning construction land standard (GB50137-2011), the property distribution of the Kun shan urban land is shown in FIG. 13.
The cost parameters of various traffic modes and expenses among traffic cells are as follows:
and (3) performing fitting analysis on the travel volume and the attraction volume of the traffic district and various land characteristics of the traffic district, and obtaining the travel rate of the various land characteristics as shown in tables 6-16:
wherein indicates a fitted significance of less than 0.01, and indicates a significance of less than 0.05. For the reliability and accuracy of modeling, only the influence of the four land characteristics of public management and public service land, commercial service industry facility land, industrial land and residential land on traffic distribution is considered in the final modeling process.
The model parameter selection table of each transportation mode is as follows:
combining traffic distribution model (ln (T) according to parameter selection tableij)=α ln(Ri(u))+β ln(Rj(u))+γ ln(Cij) + k) and utility function of each mode of transportation (F)w=ω1lw+θ1tw、Fb=ω2lb+θ2(tb+2)、Fe=ω3le+θ3(te+2)、Fp=ω4lp+θ4tp+θ5fp、Fc=ω6lc+θ6tc+θ7fc) Inputting parameter variables (numerical values of parameter codes are obtained from survey data) by using SPSS software, fitting traffic distribution models of various traffic modes, and completing parameter calibration, wherein the formula is as follows:
1. traffic distribution model by walking
ln(Tij-71.623)
=0.914ln(70.692OB+11.201OM+114.035OR)+0.865ln(52.562DB+7.533DM+81.785DR)-3.069ln(0.025lw+0.092tw)
2. Bicycle mode traffic distribution model
ln(Tij+3.734)
=0.861ln(24.118OB+6.576OM+45.843OR)+0.898ln(22.330DB+4.245DM+24.290DR)-2.203ln(0.017lb+0.003tb)
3. Electric vehicle mode traffic distribution model
ln(Tij+6.838)
=0.877ln(71.423OB+22.708OM+89.895OR)+0.962ln(55.346DA+29.553DB+43.796DM+51.883DR)-2.414ln(0.279le+0.001te)
4. Public transport mode traffic distribution model
ln(Tij-29.742)
=1.307ln(16.293OB+3.864OM+10.912OR)+1.233ln(59.861DB+16.562DM+46.743DR)-2.466ln(0.110lp+0.081tp+3.682fp)
5. Traffic distribution model by car mode
ln(Tij-38.199)
=1.051ln(9.473OB+2.557OM+8.885OR)+0.898ln(4.014DB+1.228DM+5.756DR)-1.450ln(0.095lc+0.008tc+0.052fc)
The model is tested, and the fitting degree of the multi-mode traffic distribution model is as follows:
the average level reaches 0.801, and the fitting effect of the method model is good.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (7)
1. A multi-mode traffic distribution model construction method based on mobile phone signaling data is characterized by comprising the following steps:
(1) identifying travel stopping points by using a space-time clustering algorithm according to the time-space characteristics of the base station track points, and extracting travel chain information so as to be matched with an actual road network;
(2) matching a base station in a trip chain with an intersection in a road network by a probability decision method, and acquiring trip track information of a mobile phone user in the urban road network for matching with resident trip survey data;
(3) matching resident trip survey data with trip track information in a road network by using a rule matching method, and acquiring mobile phone signaling track data with a traffic mode label as a sample space;
(4) screening characteristic parameters based on chi-square test, constructing a traffic mode division model by using a random forest classification algorithm, converting a base station OD into a travel OD between traffic cells, and finishing the estimation of the full-sample split mode travel OD through sample expansion;
(5) constructing a multi-mode traffic distribution model by using a gravity model according to the intrinsic influence of the land layout and the traffic mode on traffic distribution;
(6) and completing model parameter calibration work by using the acquired full sample sub-mode travel OD, and completing model construction.
2. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (1) comprises the following steps:
s1, acquiring base station position information corresponding to the mobile phone signaling data, and sorting all base station position information in one day according to a time sequence to extract the approximate activity position information of the user in the day;
s2, setting time, distance and speed threshold values according to a space-time clustering algorithm;
s3, dividing the track points into determined stop points, possible stop points and displacement points by using time and speed threshold parameters;
s4, performing secondary judgment on the possible stop points by using the distance threshold parameters, and finally obtaining all the determined stop points in the track points to obtain the trip chain information.
3. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (2) comprises the following steps:
s1, generating a base station coverage range through an ArcGIS neighborhood analysis tool, and then obtaining an intersection-to-road correspondence table, a base station-to-intersection correspondence table and a base station coverage range-in-road correspondence table through a spatial connection tool;
s2, numbering each travel base station track sequence, and assuming a set Si={j1,j2,…,jnDenotes a track, where jiIndicating base stations occupied in the trajectory;
s3 accumulating trace S according to the base station road corresponding tableiIn each base station jiThe covered road is obtained, and a covered road frequency table F of the track is obtainedi;
S4 for each base station jiAnd extracting intersections in the coverage range and a road set R consisting of corresponding intersections according to the correspondence table of the base stations and the intersectionsi;
S5 frequency table F obtained according to statisticsiDenotes RiRoad with second highest intermediate frequencyAnd screening the intersection consisting of the roads, and when the intersection isThen delete the base station ji;
S6, calculating the distance D between the intersection screened in the previous step and the base station, and corresponding the base station to the road network intersection according to the minimum distance principle;
s7 circularly matching all base stations in the track sequence to obtain an intersection sequence CiFor non-adjacent intersections, calling a shortest path function to connect the intersections to obtain an intersection sequence which is completely connected on a road network;
s8 circulation judgment intersection sequence CiThree adjacent middle data C(i-1),Ci,C(i+1)Whether the data is A-B-A type data or not, if so, deleting the intersection Ci,C(i+1);
S9, connecting adjacent intersections to obtain track data of the users on the road network, namely travel track information of the mobile phone users in the urban road network, and matching the travel track information with resident travel survey data.
4. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (3) comprises the following steps:
s1, acquiring gender and age of residents, the number of a departure traffic cell, the number of an arrival traffic cell, departure time and arrival time of each travel record through resident travel survey;
s2, matching the date of resident travel survey data, the departure traffic cell and the arrival traffic cell with travel track information extracted from the mobile phone signaling data, and performing primary screening;
s3, carrying out secondary screening on the mobile phone data track information according to the departure time of each resident trip survey data;
s4, performing final matching according to the gender and the age attribute, and if the matching is successful, defining the travel mode of the resident travel survey data as the travel mode corresponding to the travel track of a certain mobile phone, namely obtaining the mobile phone signaling track data with the traffic mode label.
5. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (4) comprises the following steps:
s1, fusing the mobile phone signaling data and the GPS navigation data, and extracting characteristic parameters according to the track spatio-temporal characteristics and the path navigation characteristics respectively;
s2, screening the optimal model precision under each characteristic dimension by using a Chi-square test method, namely screening by observing the deviation between an actual value and a theoretical value, wherein the test formula is as follows:
in the formula: chi2Denotes the deviation, E is the theoretical value, xiIs a sample observed value, and n is the total number of the characteristic parameters; selecting the number of the features corresponding to the highest precision;
s3, obtaining the importance of each characteristic parameter according to the following formula, analyzing the importance of the characteristic parameters, and constructing a traffic mode division model according to a random forest algorithm;
in the formula: g(p)For the importance of the characteristic parameter, K is the number of classes, pkIs the probability that the sample point belongs to the kth class;
s4, matching the base station and the traffic cell by using a traditional traffic cell division method, mainly taking administrative boundaries, using natural obstacles in the administrative district as a main division basis, adopting a surface-to-surface, point-to-surface or point-to-point matching method, and converting the base station OD into a travel OD between the traffic cells;
s5, considering the market share proportion of mobile phone operation and the popularity of mobile phones, completing sample expansion from mobile phones to mobile phone users, sample expansion from single operator to all operators, sample expansion from all mobile phone users to all travel residents, and obtaining the sub-mode OD estimation of the whole sample.
6. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (5) comprises the following steps:
s1, establishing a relation between the land with different land properties and the district traffic volume, and obtaining unit land occurrence attraction rates of various land properties through fitting;
s2, taking the travel distance as traffic impedance, extracting travel distances and travel times of different traffic modes between the same origin-destination point from the Goods API as reference factors, and respectively considering generalized cost functions of walking, bicycles, electric vehicles, buses and cars;
s3, under the condition of considering land layout influence factors, carrying out logarithmic processing on the gravity model basic model, and obtaining the cell attraction amount according to the traffic attraction rate of various land properties and the land area of corresponding properties to obtain a model formula:
ln(Tij)=αln(Ri(u))+βln(Rj(u))+γln(Cij)+k
in the formula: t isijThe traffic volume of the traffic cell i and the traffic cell j is obtained; ri(u) traffic occurrence of the departure cell i; rj(u) is the amount of traffic attraction to cell j; cijThe trip impedances of the traffic cell i and the traffic cell j are shown; alpha, beta, gamma and k are undetermined coefficients;
s4 trip impedance CijThe model formula under different modes of transportation is as follows:
utility function of walking:
Fw=ω1lw+θ1tw
in the formula: lwRepresenting a walking travel distance; t is twRepresenting a walking travel time; omega1、θ1Are all undetermined parameters.
Utility function of bicycle:
Fb=ω2lb+θ2(tb+2)
in the formula: lbRepresenting the travel distance of the bicycle; t is tbRepresenting the travel time of the bicycle; omega2、θ2Are all undetermined parameters; 2 is defined as the parking time 2 min;
utility function of electric vehicle:
Fe=ω3le+θ3(te+2)
in the formula: leRepresenting the travel distance of the electric vehicle; t is teRepresenting the travel time of the electric vehicle; omega3、θ3Are all undetermined parameters; 2 is defined as the parking time 2 min;
utility function of bus:
Fp=ω4lp+θ4tp+θ5fp
in the formula: lpRepresenting the travel distance of the bus; t is tpRepresenting the travel time of the bus; f. ofpRepresents bus ticket cost; omega4、θ4、θ5Are all undetermined parameters;
utility function of car:
Fc=ω6lc+θ6tc+θ7fc
in the formula: lcRepresenting the travel distance of the car; t is tcRepresenting the car travel time; f. ofcRepresenting the parking cost of the car; omega6、θ6、θ7Are all undetermined parameters.
7. The method for constructing a multimode traffic distribution model based on mobile phone signaling data as claimed in claim 1, characterized in that: the process of the step (6) comprises the following steps:
s1, dividing land according to the land property classification standard, connecting the land property map layer with the control gauge unit map layer by using GIS software, numbering, and calculating the area of various land properties;
s2, assuming the starting point and the ending point of travel as the gravity center of the traffic districts, acquiring the longitude and latitude of each traffic district, and crawling various traffic expenses among the traffic districts from the API of the Gagde map by using python;
s3, carrying out fitting analysis on the traffic volume and the attraction volume of the traffic cell and various land characteristics of the traffic cell to obtain the travel rate of the land characteristics of various types, and summarizing and obtaining a traffic distribution model parameter selection table of each traffic mode;
and S4, combining the obtained full-sample mode travel OD information, fitting a corresponding traffic distribution model according to a parameter selection table, and obtaining traffic distribution model formulas of various traffic modes.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2020108173733 | 2020-08-14 | ||
CN202010817373 | 2020-08-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112133090A true CN112133090A (en) | 2020-12-25 |
Family
ID=73846041
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010980271.3A Pending CN112133090A (en) | 2020-08-14 | 2020-09-17 | Multi-mode traffic distribution model construction method based on mobile phone signaling data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112133090A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112734216A (en) * | 2021-01-04 | 2021-04-30 | 长安大学 | Resident trip purpose identification method based on communication positioning data |
CN112949784A (en) * | 2021-05-13 | 2021-06-11 | 深圳市城市交通规划设计研究中心股份有限公司 | Resident trip chain model construction method and resident trip chain acquisition method |
CN113111271A (en) * | 2021-04-20 | 2021-07-13 | 智慧足迹数据科技有限公司 | Travel OD data sample expansion method and device, computer equipment and storage medium |
CN113407906A (en) * | 2021-05-13 | 2021-09-17 | 东南大学 | Method for determining traffic distribution impedance function based on mobile phone signaling data |
CN113487871A (en) * | 2021-08-13 | 2021-10-08 | 同济大学 | Rapid traffic distribution method, device and storage medium based on network aggregation strategy |
CN113569977A (en) * | 2021-08-05 | 2021-10-29 | 东南大学 | Travel purpose identification method based on mobile phone signaling data |
CN113709660A (en) * | 2021-07-30 | 2021-11-26 | 东南大学 | Method for accurately extracting travel path by using mobile phone signaling data |
CN113901109A (en) * | 2021-10-11 | 2022-01-07 | 交通运输部规划研究院 | Method for calculating total number of people and time distribution of passenger and truck travel modes on intercity highway |
CN114141008A (en) * | 2021-10-29 | 2022-03-04 | 东南大学 | Novel shared public transportation service area selection method based on mobile phone signaling data |
CN114245329A (en) * | 2021-12-21 | 2022-03-25 | 北京红山信息科技研究院有限公司 | Traffic mode identification method, device, equipment and storage medium |
CN114501419A (en) * | 2021-12-30 | 2022-05-13 | 中国联合网络通信集团有限公司 | Signaling data processing method, device and storage medium |
CN114639239A (en) * | 2022-02-24 | 2022-06-17 | 东南大学 | Improved gravity model traffic distribution prediction method |
CN114694378A (en) * | 2022-03-21 | 2022-07-01 | 东南大学 | Two-stage traffic distribution prediction method |
CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
CN115457758A (en) * | 2022-07-08 | 2022-12-09 | 北京交通大学 | Method for identifying traffic travel mode of signaling data of mobile terminal |
CN115472006A (en) * | 2022-08-26 | 2022-12-13 | 武汉大学 | Method for estimating commuting traffic flow of newly added road section of road network by utilizing mobile phone signaling data |
CN115967950A (en) * | 2023-02-17 | 2023-04-14 | 东南大学 | Inter-city travel mode identification method based on characteristics and time sequence of mobile phone signaling data |
CN116070035A (en) * | 2022-08-31 | 2023-05-05 | 荣耀终端有限公司 | Data processing method and electronic equipment |
CN116206452A (en) * | 2023-05-04 | 2023-06-02 | 北京城建交通设计研究院有限公司 | Sparse data characteristic analysis method and system for urban traffic travel |
CN116233759A (en) * | 2023-04-25 | 2023-06-06 | 北京城建交通设计研究院有限公司 | Resident travel track investigation method and system |
CN116628455A (en) * | 2023-07-25 | 2023-08-22 | 中路高科交通科技集团有限公司 | Urban traffic carbon emission monitoring and decision support method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101800927A (en) * | 2009-02-11 | 2010-08-11 | 同济大学 | Acquisition method of traffic origin-destination information based on mobile phone user arrival and departure amount |
CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
CN107040894A (en) * | 2017-04-21 | 2017-08-11 | 杭州市综合交通研究中心 | A kind of resident trip OD acquisition methods based on mobile phone signaling data |
CN109978224A (en) * | 2019-01-14 | 2019-07-05 | 南京大学 | A method of analysis obtains the Trip Generation Rate of heterogeneity building |
CN110160538A (en) * | 2019-05-09 | 2019-08-23 | 东南大学 | A kind of map-matching method based on mobile phone signaling data |
US20200245182A1 (en) * | 2019-01-29 | 2020-07-30 | Cisco Technology, Inc. | Mobile edge computing with low latency traffic segregation within a pdn using dedicated bearers |
-
2020
- 2020-09-17 CN CN202010980271.3A patent/CN112133090A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101800927A (en) * | 2009-02-11 | 2010-08-11 | 同济大学 | Acquisition method of traffic origin-destination information based on mobile phone user arrival and departure amount |
CN105117789A (en) * | 2015-07-29 | 2015-12-02 | 西南交通大学 | Resident trip mode comprehensive judging method based on handset signaling data |
CN107040894A (en) * | 2017-04-21 | 2017-08-11 | 杭州市综合交通研究中心 | A kind of resident trip OD acquisition methods based on mobile phone signaling data |
CN109978224A (en) * | 2019-01-14 | 2019-07-05 | 南京大学 | A method of analysis obtains the Trip Generation Rate of heterogeneity building |
US20200245182A1 (en) * | 2019-01-29 | 2020-07-30 | Cisco Technology, Inc. | Mobile edge computing with low latency traffic segregation within a pdn using dedicated bearers |
CN110160538A (en) * | 2019-05-09 | 2019-08-23 | 东南大学 | A kind of map-matching method based on mobile phone signaling data |
Non-Patent Citations (4)
Title |
---|
刘娟: "基于手机数据的交通出行方式识别研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
毛晓汶: "基于手机信令技术的区域交通出行特征研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
赵再先 等: "大数据时代"四阶段"交通模型体系技术升级方法", 《交通与运输 交通模型》 * |
马静 等: "基于用地结构熵的广义熵重力模型", 《长安大学学报(自然科学版)》 * |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112734216A (en) * | 2021-01-04 | 2021-04-30 | 长安大学 | Resident trip purpose identification method based on communication positioning data |
CN113111271A (en) * | 2021-04-20 | 2021-07-13 | 智慧足迹数据科技有限公司 | Travel OD data sample expansion method and device, computer equipment and storage medium |
CN113111271B (en) * | 2021-04-20 | 2023-08-29 | 智慧足迹数据科技有限公司 | Trip OD data sample expansion method and device, computer equipment and storage medium |
CN112949784A (en) * | 2021-05-13 | 2021-06-11 | 深圳市城市交通规划设计研究中心股份有限公司 | Resident trip chain model construction method and resident trip chain acquisition method |
CN113407906A (en) * | 2021-05-13 | 2021-09-17 | 东南大学 | Method for determining traffic distribution impedance function based on mobile phone signaling data |
CN112949784B (en) * | 2021-05-13 | 2021-10-29 | 深圳市城市交通规划设计研究中心股份有限公司 | Resident trip chain model construction method and resident trip chain acquisition method |
CN113407906B (en) * | 2021-05-13 | 2024-02-02 | 东南大学 | Method for determining traffic travel distribution impedance function based on mobile phone signaling data |
CN113709660B (en) * | 2021-07-30 | 2022-06-24 | 东南大学 | Method for accurately extracting travel path by using mobile phone signaling data |
CN113709660A (en) * | 2021-07-30 | 2021-11-26 | 东南大学 | Method for accurately extracting travel path by using mobile phone signaling data |
CN113569977A (en) * | 2021-08-05 | 2021-10-29 | 东南大学 | Travel purpose identification method based on mobile phone signaling data |
CN113569977B (en) * | 2021-08-05 | 2022-11-18 | 东南大学 | Travel purpose identification method based on mobile phone signaling data |
CN113487871A (en) * | 2021-08-13 | 2021-10-08 | 同济大学 | Rapid traffic distribution method, device and storage medium based on network aggregation strategy |
CN113901109B (en) * | 2021-10-11 | 2022-11-18 | 交通运输部规划研究院 | Method for calculating total number of people and time distribution of passenger and truck travel modes on intercity highway |
CN113901109A (en) * | 2021-10-11 | 2022-01-07 | 交通运输部规划研究院 | Method for calculating total number of people and time distribution of passenger and truck travel modes on intercity highway |
CN114141008A (en) * | 2021-10-29 | 2022-03-04 | 东南大学 | Novel shared public transportation service area selection method based on mobile phone signaling data |
CN114245329A (en) * | 2021-12-21 | 2022-03-25 | 北京红山信息科技研究院有限公司 | Traffic mode identification method, device, equipment and storage medium |
CN114501419B (en) * | 2021-12-30 | 2023-05-12 | 中国联合网络通信集团有限公司 | Signaling data processing method, apparatus and storage medium |
CN114501419A (en) * | 2021-12-30 | 2022-05-13 | 中国联合网络通信集团有限公司 | Signaling data processing method, device and storage medium |
CN114639239A (en) * | 2022-02-24 | 2022-06-17 | 东南大学 | Improved gravity model traffic distribution prediction method |
CN114694378A (en) * | 2022-03-21 | 2022-07-01 | 东南大学 | Two-stage traffic distribution prediction method |
CN114694378B (en) * | 2022-03-21 | 2023-02-14 | 东南大学 | Two-stage traffic distribution prediction method |
CN115457758A (en) * | 2022-07-08 | 2022-12-09 | 北京交通大学 | Method for identifying traffic travel mode of signaling data of mobile terminal |
CN115457758B (en) * | 2022-07-08 | 2024-02-20 | 北京交通大学 | Mobile terminal signaling data traffic travel mode identification method |
CN114999162A (en) * | 2022-08-02 | 2022-09-02 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
CN115472006A (en) * | 2022-08-26 | 2022-12-13 | 武汉大学 | Method for estimating commuting traffic flow of newly added road section of road network by utilizing mobile phone signaling data |
CN116070035A (en) * | 2022-08-31 | 2023-05-05 | 荣耀终端有限公司 | Data processing method and electronic equipment |
CN116070035B (en) * | 2022-08-31 | 2023-10-20 | 荣耀终端有限公司 | Data processing method and electronic equipment |
CN115967950A (en) * | 2023-02-17 | 2023-04-14 | 东南大学 | Inter-city travel mode identification method based on characteristics and time sequence of mobile phone signaling data |
CN116233759A (en) * | 2023-04-25 | 2023-06-06 | 北京城建交通设计研究院有限公司 | Resident travel track investigation method and system |
CN116233759B (en) * | 2023-04-25 | 2023-07-28 | 北京城建交通设计研究院有限公司 | Resident travel track investigation method and system |
CN116206452A (en) * | 2023-05-04 | 2023-06-02 | 北京城建交通设计研究院有限公司 | Sparse data characteristic analysis method and system for urban traffic travel |
CN116206452B (en) * | 2023-05-04 | 2023-08-15 | 北京城建交通设计研究院有限公司 | Sparse data characteristic analysis method and system for urban traffic travel |
CN116628455A (en) * | 2023-07-25 | 2023-08-22 | 中路高科交通科技集团有限公司 | Urban traffic carbon emission monitoring and decision support method and system |
CN116628455B (en) * | 2023-07-25 | 2023-10-03 | 中路高科交通科技集团有限公司 | Urban traffic carbon emission monitoring and decision support method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112133090A (en) | Multi-mode traffic distribution model construction method based on mobile phone signaling data | |
CN111653099B (en) | Bus passenger flow OD obtaining method based on mobile phone signaling data | |
Veloso et al. | Sensing urban mobility with taxi flow | |
CN109561386A (en) | A kind of Urban Residential Trip activity pattern acquisition methods based on multi-source location data | |
CN111653096B (en) | Urban trip mode identification method based on mobile phone signaling data | |
CN110909434B (en) | Urban public transport trunk line network design method under low-carbon guidance | |
Zhang et al. | Green travel mobility of dockless bike-sharing based on trip data in big cities: A spatial network analysis | |
CN115168529B (en) | Hub passenger flow tracing method based on mobile phone positioning data | |
CN105844031B (en) | A kind of urban transportation gallery recognition methods based on mobile phone location data | |
CN111341135B (en) | Mobile phone signaling data travel mode identification method based on interest points and navigation data | |
CN110413855B (en) | Region entrance and exit dynamic extraction method based on taxi boarding point | |
CN112000755A (en) | Regional trip corridor identification method based on mobile phone signaling data | |
Ji et al. | Research on classification and influencing factors of metro commuting patterns by combining smart card data and household travel survey data | |
CN117056823A (en) | Method and system for identifying occupation type of shared bicycle commuter user | |
CN113573238B (en) | Method for identifying trip passenger trip chain based on mobile phone signaling | |
CN113079463A (en) | Tourist attraction tourist travel activity identification method based on mobile phone signaling data | |
CN109800903A (en) | A kind of profit route planning method based on taxi track data | |
Chung et al. | Investigating the effects of POI-based land use on traffic accidents in Suzhou Industrial Park, China | |
Tian et al. | Identifying residential and workplace locations from transit smart card data | |
CN114141008B (en) | Shared public transportation service area selection method based on mobile phone signaling data | |
CN113569977B (en) | Travel purpose identification method based on mobile phone signaling data | |
Lwin et al. | Identification of various transport modes and rail transit behaviors from mobile CDR data: A case of Yangon City | |
Wang et al. | Exploring the Spatial Variation of Access/Egress Distances of Subway Stations Using Mobile Phone Positioning Data in Chengdu, China | |
CN110942622B (en) | Parking lot planning method based on real-time operation big data of parking lot | |
Mamdoohi et al. | An Analysis of Public Transit Connectivity Index in Tehran. The Case Study: Tehran Multi-Modal Transit Network |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201225 |