CN115827643A - Travel chain feature extraction method based on resident activities - Google Patents
Travel chain feature extraction method based on resident activities Download PDFInfo
- Publication number
- CN115827643A CN115827643A CN202310096115.4A CN202310096115A CN115827643A CN 115827643 A CN115827643 A CN 115827643A CN 202310096115 A CN202310096115 A CN 202310096115A CN 115827643 A CN115827643 A CN 115827643A
- Authority
- CN
- China
- Prior art keywords
- chain
- trip
- resident
- travel
- stop
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a trip chain feature extraction method based on resident activities, and belongs to the technical field of trip chain feature extraction. The method comprises the following steps: s1, acquiring urban resident trip survey data to obtain resident trip activity data; s2, obtaining resident activity stay point data; s3, extracting the active chain of each resident all day, and writing the travel attribute feature information of each stay point into an active chain dictionary; s4, splitting the activity chain of the resident all day into a plurality of different resident trip chains, acquiring trip attribute information of the stay points corresponding to the activity chain of the all day, and writing the trip attribute information into a trip chain dictionary; s5, splitting the travel chain of the resident into basic travel chains of the resident, acquiring travel attribute information corresponding to the stop points, and writing the travel attribute information into a basic travel chain dictionary; and S6, extracting the travel characteristic information of the resident travel chain according to the basic travel chain. The problem of the analysis structure precision that is poor that the deep analysis of not carrying out the whole day trip chain to individual leads to is solved.
Description
Technical Field
The application relates to a feature extraction method, in particular to a trip chain feature extraction method based on resident activities, and belongs to the technical field of trip chain feature extraction.
Background
With the continuous development and perfection of urban space layout and infrastructure, the travel demand of urban residents is increasing day by day, the personnel activity rule is changing constantly, the operation of urban road traffic and public traffic is more complex, and how to study and judge the urban space layout and the personnel activity characteristics according to the urban resident activity is particularly critical to provide scientific support for traffic planning construction decisions such as urban space, traffic demand analysis, traffic facility planning, traffic policy evaluation, bus passenger flow analysis and the like.
Resident trip characteristic analysis results obtained from resident trip survey data are important reference bases for urban space and traffic planning, but the traditional resident trip characteristic analysis mainly uses single trip as an analysis unit, and the method does not carry out deep analysis on time, traffic mode, activity types of staying points and the like of a personal all-day trip chain including multiple continuous trips of a person in one day, and is difficult to meet increasingly refined and complicated traffic demand analysis, so that the analysis result precision is insufficient.
Disclosure of Invention
The following presents a simplified summary of the invention in order to provide a basic understanding of some aspects of the invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to determine the key or critical elements of the present invention, nor is it intended to limit the scope of the present invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
In view of the above, in order to solve the technical problem of poor analysis structure precision caused by not performing deep analysis on the personal all-day trip chain in the prior art, the invention provides a trip chain feature extraction method based on the activities of residents;
the first scheme is as follows: a travel chain feature extraction method based on resident activities comprises the following steps:
s1, acquiring urban resident trip survey data to obtain resident trip activity data;
s2, preprocessing resident trip activity data to obtain resident activity stay point data;
s3, traversing the stay point data of each resident, extracting the active chain of each resident all day, and writing the travel attribute feature information of each stay point into an active chain dictionary;
s4, traversing the all-day active chain of each resident, splitting the all-day active chain of the resident into a plurality of different resident trip chains, acquiring trip attribute information of a stop point corresponding to the all-day active chain, and writing the trip attribute information into a trip chain dictionary;
s5, traversing the travel chain of each resident, splitting the travel chain of each resident into resident basic travel chains, acquiring travel attribute information of a stop point corresponding to the basic travel chains, and writing the travel attribute information into a basic travel chain dictionary;
and S6, extracting the travel characteristic information of the resident travel chain according to the basic travel chain with the travel attribute information.
Preferably, the resident trip activity data includes a resident ID, a family ID, a personal occupation type, a stop point order, a stop point longitude, a stop point latitude, a stop point departure time, a stop point arrival time, a stop point trip purpose code, a stop point trip mode and an all-day activity starting point.
Preferably, the method for preprocessing the resident travel activity data comprises the following steps: and matching the urban traffic district, administrative district and zone elimination stay point trip purpose empty resident trip records according to the longitude and latitude information of the resident activity stay point by combining the geographic information data of the urban traffic district.
Preferably, the specific method of S3 is as follows: the method comprises the following steps:
s31, reading resident activity stop point data, grouping according to resident IDs, sequencing from morning to evening according to the time sequence of the resident activity stop points, and obtaining codes of all-day travel starting points of residents;
s32, presetting codes of starting points of the resident activity chains as the travel starting points of the residents all day, traversing all activity stop points of the residents all day, sequentially linking the travel destination codes of the activity stop points to the resident activity chains, and splicing the travel destination codes with the travel destination codes of the stop points in the previous sequence;
and S33, after traversing all the resident activity stop point information, generating a resident activity chain and corresponding stop point travel attribute information, writing the resident activity chain and the corresponding stop point travel attribute information into an activity chain dictionary, and finishing the extraction of the resident all-day activity chain.
Preferably, the specific method of S4 is as follows: the method comprises the following steps:
s41, reading all resident activity chains and corresponding trip attribute information of the stop points;
s42, traversing the one-day activity chain and corresponding trip attribute information of each resident;
s43, splitting the activity chain with the start end and the end of the activity chain as 'home' into 'home-home' trip chains, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into a trip chain dictionary;
s44, further splitting a working 'home-home' trip chain contained in the trip chain dictionary in the S42, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into the trip chain dictionary;
s45, directly reserving the active chains of which the starting and ending points of the active chains are not completely 'home', acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into a trip chain dictionary;
and S46, after traversing all the resident activity chains, generating a resident trip chain and trip attribute information of a corresponding stop point, writing the resident trip chain and the trip attribute information into a trip chain dictionary, and finishing the extraction of the resident trip chain.
Preferably, the specific method of S43 is: the method comprises the following steps:
s431, reading a movable chain with a start point and an end point of a resident as 'home' and travel attribute information of a corresponding stop point;
s432, removing duplication of stop points continuously appearing in the active chain, and keeping the stop points appearing for the first time or the last time and travel attribute information;
s433, presetting an empty list corresponding to the trip chain to be split for each active chain, performing cycle traversal on the active chain stop points with the starting end and the ending end being H, sequentially reading the stop point codes and the corresponding trip attribute information,
s434, directly adding the stop point codes of the stop points, which are not home, in the middle of the active chain into the trip chain to be extracted, cutting off the positions, which are home, of the stop points in the middle of the active chain, extracting the trip chain of home, and correspondingly extracting the trip attribute information of the stop points corresponding to the trip chain;
s435, taking the cut-off stop point in S434 as the starting point of the next trip chain, and cutting off when meeting the stop point of 'home' until the terminal 'home' of the traversing active chain stops;
and S436, after traversing all resident activity chains, completing the separation of the activity chains according to the 'home-home' trip chain, acquiring the trip attribute information of the corresponding stop point, writing the attribute information into a trip chain dictionary, and completing the extraction of the resident 'home-home' trip chain.
Preferably, the specific method of S44 is: the method comprises the following steps:
s441, reading a trip chain with a resident starting point and a resident finishing point as 'home' and trip attribute information of a corresponding stop point;
s442, traversing each travel chain of each resident, counting the number w _ num of 'working' stop points contained in the travel chain, if the w _ num is smaller than or equal to 1, directly keeping the original travel chain, and if the w _ num is larger than 1, executing the next step;
s443, extracting a position index start _ index of a first occurrence of a 'working' stop point in a trip chain and a position index end _ index of a last occurrence of the 'working' stop point as a cut-off position of trip chain splitting;
s444, further splitting the trip chain according to the index position of work in the trip chain, splitting the trip chain containing more than 3 stop points into a trip chain with a start point and an end point as home, wherein the middle stop point only contains the trip chain of home with the stop points of 1 work and the trip chain of work with the start point and the end point as work;
s445, further splitting the work/work trip chain with the starting point and the ending point of the work in the S444, and splitting the trip chain containing more than 2 work stop points into a plurality of work/work trip chains only containing 2 work/work stop points;
and S446, after traversing all resident trip chains, splitting the trip chain with the starting and ending points of ' home and ' work ' for the second round, and acquiring the trip attribute information of the corresponding stop point.
Preferably, the specific method of S5 is as follows: the method comprises the following steps:
s51, reading a resident trip chain and trip attribute information of a corresponding stop point;
s52, presetting the priority of non-key stop points of the resident trip chain, and ensuring that the stop points with higher priority are reserved in the process of splitting the basic trip chain of residents by the resident trip chain;
s53, traversing each travel chain of each resident, and sequentially reading the stop point codes and the corresponding stop point travel attribute information in the travel chains;
s54, splitting non-key stop points in the 'home' trip chain, traversing the stop points with preset priorities according to the priority order aiming at the 'home' trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
s55, splitting non-key stop points in the 'working star working' trip chain, traversing the stop points with preset priorities according to the priority order aiming at the 'working star working' trip chain, judging whether the trip chain comprises the corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
s56, splitting non-key stop points in the 'home' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'home' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
s57, splitting non-key stop points in the 'working-start' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'working-start' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
and S58, after traversing all resident trip chains, splitting the resident trip chain to finish the basic trip chain, acquiring the trip attribute information of the corresponding stop point, writing the attribute information into a basic trip chain dictionary, and finishing the extraction of the resident basic trip chain.
Scheme II: an electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the resident activity-based travel chain feature extraction method when executing the computer program.
The third scheme is as follows: a computer-readable storage medium on which a computer program is stored, the computer program implementing a resident activity-based travel chain feature extraction method according to aspect one when executed by a processor.
The invention has the following beneficial effects: the method comprises the steps of extracting the travel attribute information of the resident activity chain and the corresponding staying point all day according to resident activity data; extracting travel attribute information of a plurality of different travel chains and corresponding stop points of the residents all day according to the information of the activity chains of the residents all day; extracting the travel attribute information of the resident basic travel chain and the corresponding stop point according to the resident travel chain information; and finally, extracting the trip chain characteristics of the residents such as the trip and return trip purposes, the trip and return departure time, the trip and return arrival time, the trip and return traffic mode, the trip and return departure and arrival traffic district and the like of different trip chains in one day according to the basic trip chain information of the residents. The invention effectively utilizes the resident all-day trip information and solves the technical problem of poor analysis structure precision caused by not carrying out deep analysis on the individual all-day trip chain in the prior art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow chart of a travel chain feature extraction method based on resident activities according to the invention;
FIG. 2 is a schematic view of the daily activity chain and the staying point of the residents according to the present invention.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Embodiment 1, this embodiment is described with reference to fig. 1 to 2, and a method for extracting characteristics of a travel chain based on activities of residents includes the following steps:
s1, acquiring urban resident trip survey data to obtain resident trip activity data;
the resident trip activity data comprises a resident ID, a family ID, an individual occupation type, a stop point sequence, a stop point longitude, a stop point latitude, a stop point departure time, a stop point arrival time, a stop point trip purpose code, a stop point trip mode and an all-day activity starting point;
specifically, taking a trip survey of residents in a certain city as an example, referring to a resident survey data table in table 1, the trip purpose of the residents in the city comprises 9 categories which are respectively a home (H), a work (W), a business (B), casual shopping (S), a sender (C), a middle and primary school (E), a university (U), an office (F) and other purposes (O), wherein letters in brackets are preset codes corresponding to the trip purpose;
TABLE 1 resident survey data sheet
| Resident ID | Family ID | Type of occupation | Order of stop points | Dwell point longitude | Latitude of stagnation point | Time of departure | Time of arrival | Purpose of trip | Coding for trip purpose | Travel mode | Whole day activity starting point | |
| 1 | 1 | Others | 0 | 120.26 | 31.54 | 800 | 810 | Working hours | W | Self-contained bicycle | H | |
| 2 | 1 | Others | 1 | 120.27 | 31.54 | 1640 | 1650 | Sleep/rest | H | Self-contained bicycle | H | |
| 3 | 1 | Leave the retirement staff | 0 | 120.27 | 31.53 | 830 | 835 | Shopping | S | Electric vehicle | H | |
| 4 | 2 | Leave the retired person | 1 | 120.27 | 31.54 | 900 | 905 | Housework/caretaker | H | Electric vehicle | H | |
| 5 | 2 | Officer | 0 | 120.21 | 31.55 | 830 | 835 | Work in office | W | Walking device | H | |
| 6 | 2 | Officer | 1 | 120.21 | 31.55 | 1300 | 1400 | Business outing | B | | H | |
| 7 | 3 | Officer | 2 | 120.25 | 31.55 | 1700 | 1830 | Sleep/rest | H | Public transport | H | |
| 8 | 3 | Office clerk | 0 | 120.26 | 31.54 | 810 | 813 | Work in office | W | Electric vehicle | H | |
| … | … | … | … | … | … | … | … | … | … | … | … |
S2, preprocessing resident trip activity data to obtain resident activity stay point data;
matching city traffic districts, administrative areas and zone rejection stop point trip records with empty resident trip records according to the longitude and latitude information of the resident activity stop points by combining the geographic information data of the city traffic districts;
the purpose of this step is to facilitate to count the characteristic set of the resident's individual trip to the predetermined traffic area scope, improve the recognition degree that the characteristic of resident's trip chain excavates; the problem of jumping of a stay point is avoided in the trip chain generation, and preprocessed resident activity stay point information is obtained;
s3, traversing the stay point data of each resident, such as sequentially setting the destination of the activity stay points of a certain resident all day as a home (H), a receiver (C), a worker (W), a home (H), a worker (W) and a home (H), extracting an activity chain of each resident all day, and writing the travel attribute feature information of each stay point into an activity chain dictionary; the travel attribute feature information corresponding to the stay point is marked, and is written into an activity chain dictionary (activity _ chain _ fact) for calling the subsequent travel chain information;
the travel attribute characteristics comprise departure and arrival positions, time and traffic modes;
s31, reading resident activity stop point data, grouping according to resident IDs, sequencing from morning to evening according to the time sequence of the resident activity stop points, and acquiring a coded home (H) of a resident all-day trip starting point, wherein the coded home (H) is selected from a sender (C), a worker (W), another worker (O), a worker (W), a home (H), a worker (W) and a home (H);
s32, presetting a code of a starting point end of a resident activity chain as a resident all-day trip starting point, traversing all activity stop points of the resident all day, sequentially linking a trip purpose code of the activity stop points to the resident activity chain, and splicing the code with a stop point trip purpose code of the previous sequence to obtain the resident activity chain as HCWOWHWHWH;
and S33, after traversing all the resident activity stop point information, generating a resident activity chain and corresponding stop point travel attribute information, writing the resident activity chain and the corresponding stop point travel attribute information into an activity chain dictionary (activity _ chain _ fact), and finishing the extraction of the resident all-day activity chain.
S4, traversing each resident ID, reading a movable chain dictionary, extracting all-day movable link information corresponding to the resident, traversing an all-day movable chain of each resident, splitting the all-day movable chain of the resident into a plurality of different resident trip chains, acquiring trip attribute information of a stop point corresponding to the all-day movable chain, and writing the trip attribute information into a trip chain dictionary (travel _ chain _ fact);
the activity chain information of the residents is represented in the activity chain dictionary as follows:
{ "resident 1":
{“activity_chain”:“HCWOWHWH”,
“lng”:[120.36,120.29,120.28,120.17,120.28,120.36,120.28,120.36],
“lat”:[32.89,32.87,32.98,32.47,32.98,32.89,32.98,32.89],
“taz”:[1,2,3,3,3,1,3,1],
“county”:[1,1,1,1,1,1,1,1],
“area”:[1,1,1,1,1,1,1,1],
“depature_time”:[None,630,700,830,900,1100,1130,1630],
“arrival_time”:[None,645,715,850,920,1110,1145,1645]},
none, ' private car self-driving ', ' walking ', ' private car self-driving ', ' all-resident activity chain information extraction is completed.
S41, reading a movable chain dictionary, and reading all resident movable chains and corresponding trip attribute information of a stop point;
s42, traversing the one-day activity chain and corresponding trip attribute information of each resident;
s43, splitting the active chain with the start end and the end as 'home' into 'home-home' trip chains, acquiring corresponding trip attribute information, and writing the trip attribute information into a trip chain dictionary;
s431, reading a movable chain with a resident starting point and a resident ending point as 'home' and travel attribute information of a corresponding stop point; if the active chain of the resident in one day is HCWOOWHWH, the index sequence of the active stop points is {0,1,2,3,4,5,6,7,8};
s432, carrying out duplicate removal on stop points continuously appearing in a movable chain (resident miss filling or stop conditions with short intervals continuously appear for multiple times), selecting and retaining the stop points appearing for the first time or the last time and travel attribute information according to the importance degree of different movable stop points, and if the same stop points appearing for the first time are retained after the duplicate removal, determining that the movable chain for the duplicate removal is HCWOWHWH, wherein the index sequence of the movable stop points is {0,1,2,3,5,6,7}; if the same stop point appearing at the last time is reserved after the duplication removal, the movable chain for the duplication removal is HCWOWHWHWHWH, the index sequence of the movable stop points is {0,1,2,3,4,6,7}, and the travel attribute information corresponding to the stop points is extracted according to the index sequence of the stop points;
s433, presetting an empty list _ travel _ chain corresponding to each active chain to be split into trip chains, circularly traversing the active chain stop points with the starting end and the ending end as H, and sequentially reading the stop point codes and corresponding trip attribute information, wherein if the resident active chain is HCWOWHWHWH, the index sequence of the stop points is {0,1,2,3,4,5,6,7};
s434, directly adding the stop point codes of the stop points, which are not home, in the middle of the active chain into the trip chain to be extracted, cutting off the positions, which are home, of the stop points in the middle of the active chain, extracting the trip chain of home, and correspondingly extracting the trip attribute information of the stop points corresponding to the trip chain; for chains with the index sequence of the stop points being {0,1,2,3,4,5,6,7}, namely, truncation is carried out at the position with the index sequence being ' 6 ', a trip chain of ' home is extracted as HCWOWH, and the stop point trip attribute information corresponding to the trip chain is correspondingly extracted;
s435, taking the cut-off stop point in the S434 as a starting point of the next trip chain, and cutting off when meeting the 'home' stop point until the 'home' of the movable chain terminal is traversed and stopped; for chains with the index sequence of the stop points being {0,1,2,3,4,5,6,7}, taking the stop point corresponding to the position with the index sequence of '6' as the starting point of the next trip chain to be split, similarly, if traversing to the stop point of 'home (H)', performing truncation until the traversal of the active chain terminal 'home (H)', stops, and finally splitting the obtained trip chains into HCWOWH and HWH respectively;
and S436, after traversing all resident activity chains, completing the separation of the activity chains according to the 'home-home' trip chain, acquiring the trip attribute information of the corresponding stop point, writing the attribute information into a trip chain dictionary, and completing the extraction of the resident 'home-home' trip chain. And completing the splitting and extraction of the travel chain of the first round of residents 'home'. In step S43, the resident activity chain splitting extracts the representation of the first round trip chain in the trip chain dictionary as follows:
{ "residents 1":
{“activity_chain”:“HCWOOWHWH”,
“travel_chain”:[“HCWOWH”,“HWH”]
“lng”:[[120.36,120.29,120.28,120.19,120.28,120.36],[120.36,120.28,120.36]],
“lat”:[[32.89,32.87,32.98,32.47,32.98,32.89],[32.89,32.98,32.89]],
“taz”:[[1,2,3,3,3,1],[1,3,1]],
“county”:[[1,1,1,1,1,1],[1,1,1]],
“area”:[[1,1,1,1,1,1],[1,1,1]],
“depature_time”:[None,630,700,830,900,1100],[1100,1130,1630],
“arrival_time”:[None,645,715,850,920,1110],[1110,1145,1645]},
"trans _ mode" [ [ None, 'private car self-driving', 'walking', 'private car self-driving', ], [ 'private car self-driving', 'private car self-driving' } }.
S44, further splitting a working 'home-home' trip chain contained in the trip chain dictionary in the S42, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into the trip chain dictionary;
s441, reading a trip chain with a resident starting point and a resident finishing point as 'home' and trip attribute information of a corresponding stop point; if a certain trip chain in a day of a resident is HCWOWBWH, the index sequence of the activity stop points is {0,1,2,3,4,5,6,7};
s442, traversing each travel chain of each resident, counting the number w _ num of 'working' stop points contained in the travel chain, if the w _ num is smaller than or equal to 1, directly keeping the original travel chain, and if the w _ num is larger than 1, executing the next step;
s443, extracting a position index start _ index of a first occurrence of a 'working' stop point in a trip chain and a position index end _ index of a last occurrence of the 'working' stop point as a cut-off position of trip chain splitting; for the number of "work (W)" stop points included in the trip chain hcwh is 2, the index start _ index of "W" in the trip chain is "2", and the index end _ index is "6".
S444, further splitting the trip chain according to the index position of work in the trip chain, splitting the trip chain containing more than 3 stop points into a trip chain with a start point and an end point as home, wherein the middle stop point only contains the trip chain of home with the stop points of 1 work and the trip chain of work with the start point and the end point as work;
if the selection index sequence is { [0: the starting point and the ending point of the trip chain of start _ index ] + [ end _ index: ] are 'home (H)', the middle stop point only comprises a 'home (H)' trip chain of 1 'work (W)' stop point, and the last 'work (W)' stop point is selected as a main stop point in the 'home (H)' trip chain, so that the trip from work to home in the trip chain is ensured to be one actual trip. Selecting a trip chain with an index sequence of { [ start _ index: end _ index +1] } as a 'working \/working \ (W \) trip chain with a starting point and an end point of' working \ (W) }; for the trip chain HCWOWBWH, the start point and the end point obtained by splitting are 'home (H)', the trip chain of 'home (H)' of which the middle stop point only comprises 1 'work (W)' stop point is HCWH, and the corresponding index sequence is {0,1,6,7}; splitting to obtain a work-work (W-W) trip chain with a start point and an end point of work (W), wherein the work-work (W-W) trip chain is WOWBW, and the corresponding index sequence is {2,3,4,5,6};
s445, further splitting the work/work trip chain with the starting point and the ending point of the work in the S444, and splitting the trip chain containing more than 2 work stop points into a plurality of work/work trip chains only containing 2 work/work stop points;
for example, a trip chain containing more than 2 work (W) stop points is split into a plurality of work (W) trip chains containing only 2 work (W) stop points. And traversing the stop points contained in the trip chain in sequence, directly adding the stop point codes which are not the work (W) into the trip chain to be extracted, cutting the position of the stop point in the middle of the trip chain, which is the work (W), extracting the work (W) trip chain, taking the stop point of the work (W) at the cut position as the starting point of the next trip chain, similarly cutting the stop point in the middle of the work (W), stopping the work (W) at the terminal of the trip chain, extracting other work (W) trip chains, and correspondingly extracting the stop point trip attribute information corresponding to the trip chain. Step 4.4.4, the work/work (W/W) trip chain with the start and end point of work (W) is WOWBW, the index sequence is {2,3,4,5,6}, the cutting is performed at the position with the index sequence of 4 ', WOW is extracted, the position with the index sequence of 4 is used as the start point of the next trip chain to be split, the cutting is performed if traversing to the middle stop point of work (W), and the trip chain is stopped until traversing the end point of work (W)', and finally the split trip chains are WOW and WBW respectively;
and S446, after traversing all resident trip chains, splitting the trip chain with the starting and ending points of ' home and ' work ' for the second round, and acquiring the trip attribute information of the corresponding stop point.
If the resident trip chain is split and a second round trip chain is extracted, the embodiment of the second round trip chain in the trip chain dictionary is as follows:
{ "residents 1":
{“activity_chain”:“HCWOWBWHWH”,
“travel_chain”:[“HCWH”,“WOW”,“WBW”,“HWH”]
“lng”:[[120.36,120.29,120.28,120.36],[120.19,120.28,120.19],[120.19,120.32,120.19],[120.36,120.28,120.36]]，
“lat”:[[32.89,32.87,32.98,32.89],[32.98,32.21,32.98],[32.98,32.58,32.98],[32.89,32.98,32.89]],
“taz”:[[1,2,3,3],[3,3,3],[3,3,3],[1,3,1]],
“county”:[[1,1,1,1],[1,1,1],[1,1,1],[1,1,1]],
“area”:[[1,1,1,1],[1,1,1],[1,1,1],[1,1,1]],
“depature_time”:[None,630,700,830],[830,900,1100],[1100,1110,1120],[1200,1130,1630],
“arrival_time”:[None,645,715,850],[840,920,1110],[1200,1120,1130],[1230,1145,1645]},
<xnotran> "trans _ mode": [ [ None, ' ', ' ', ' ' ], [ ' ', '', '' ], [ '', '', ' ' ], [ ' ', ' ', ' ' ] }. </xnotran>
S45, directly reserving the active chains of which the starting and ending points of the active chains are not completely home, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into a trip chain dictionary;
and S46, after traversing all the resident activity chains, generating a resident trip chain and trip attribute information of a corresponding stop point, writing the resident trip chain and the trip attribute information into a trip chain dictionary, and finishing the extraction of the resident trip chain.
S5, traversing each resident ID, reading the active chain dictionary, extracting the trip chain information corresponding to the resident, traversing the trip chain of each resident, splitting the trip chain of the resident into resident basic trip chains, acquiring the trip attribute information of a corresponding stop point of the basic trip chains, and writing the trip attribute information into the basic trip chain dictionary (basic _ travel _ chain _ fact);
s51, reading a resident trip chain and trip attribute information of a corresponding stop point;
s52, presetting the priority of non-key stop points of the resident trip chain, and ensuring that the stop points with higher priority are reserved in the process of splitting the basic trip chain of residents by the resident trip chain;
if the priority of the non-key stop point is preset to be { work (W) } middle and primary schools (E) } university (U) } business (B) } office (F) } recipient (C) } casual shopping (S) } other purposes (O) };
s53, traversing each travel chain of each resident, and sequentially reading the stop point codes and the corresponding stop point travel attribute information in the travel chains;
s54, splitting non-key stop points in the 'home' trip chain, traversing the stop points with preset priorities according to the priority order aiming at the 'home' trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
if the resident trip chain is HCWH, sequentially traversing the non-critical stop point priority sequence, and obtaining that the non-critical stop point with the highest priority in the trip chain is a 'working (W)' stop point, so that a basic trip chain only containing the 'working (W)' stop point is extracted as HWH, and trip attribute information of the corresponding stop point is obtained.
S55, splitting non-key stop points in the 'working-on' trip chain, traversing the stop points with preset priorities according to the priority order of the 'working-on' trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
if the resident trip chain is WOBW, sequentially traversing the priority sequence of the non-critical stop points, and obtaining that the non-critical stop point with the highest priority in the trip chain is a business (B) stop point, so that a basic trip chain only containing the business (B) stop point is extracted as WBW, and obtaining the trip attribute information of the corresponding stop point.
S56, splitting non-key stop points in the 'home' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'home' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
if the resident half trip chain is HCB, sequentially traversing the non-key stop point priority sequence, and obtaining that the non-key stop point with the highest priority in the trip chain is a business (B) stop point, so that the half trip chain only containing the business (B) stop point is extracted as HB, and obtaining the trip attribute information of the corresponding stop point.
S57, splitting non-key stop points in the 'working-start' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'working-start' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
if the resident half trip travel chain is WSB, sequentially traversing the non-key stop point priority sequence, and obtaining that the non-key stop point with the highest priority in the travel chain is a business (B) stop point, so that the half trip travel chain only containing the business (B) stop point is extracted as WB, and obtaining the travel attribute information of the corresponding stop point.
And S58, after traversing all resident trip chains, splitting the resident trip chain to finish the basic trip chain, acquiring corresponding trip point trip attribute information, writing the attribute information into a basic trip chain dictionary, and finishing resident basic trip chain extraction.
In step S44, the embodiment of the resident trip chain splitting and extracting basic trip chain in the trip chain dictionary is:
{ "resident 1":
{“activity_chain”:“HCWOWBWHWH”,
“basic_travel_chain”:[“HWH”,“WOW”,“WBW”,“HWH”]
“lng”:[[120.36,120.28,120.36],[120.19,120.28,120.19],[120.19,120.32,120.19],[120.36,120.28,120.36]]，
“lat”:[[32.89,32.98,32.89],[32.98,32.21,32.98],[32.98,32.58,32.98],[32.89,32.98,32.89]],
“taz”:[[1,2,3],[3,3,3],[3,3,3],[1,3,1]],
“county”:[[1,1,1],[1,1,1],[1,1,1],[1,1,1]],
“area”:[[1,1,1],[1,1,1],[1,1,1],[1,1,1]],
“depature_time”:[None,700,1130],[830,900,1100],[1100,1110,1120],[1120,1330,1630],
“arrival_time”:[None,715,1150],[840,920,1110],[1200,1120,1130],[1130,1350,1645]},
"trans _ mode": [ None, 'private car self-driving', 'private car self-driving', 'walking', 'private car self-driving', 'driving', etc. ], and a vehicle having a predetermined driving pattern is driven by the vehicle.
S6, traversing each resident ID, reading a basic trip chain dictionary, extracting different basic trip chains corresponding to the resident, and extracting trip characteristic information of the resident trip chain according to the basic trip chain with trip attribute information.
And constructing a resident trip chain generation and feature extraction result table (referring to table 2. The resident trip chain generation and feature extraction table) according to the trip feature information of the resident trip chain, wherein the resident trip chain generation and feature extraction result table comprises a go-return trip purpose, a go-return trip time, a go-return trip arrival time, a go-return trip traffic mode, a go-return trip arrival traffic district and the like. For example, the activity chain of a resident is 'home-casual shopping-home-work-casual shopping-home (HSHWSH)' one day, the travel chain is divided into 'home-casual shopping-home (HSH)' and 'home-work-casual shopping-home (HWSH)', and the basic travel chain is further divided into 'home-casual shopping-home (HSH)' and 'home-work-home (HWH)'. Wherein the departure traffic cell of "home-leisure shopping-home (HSH)" is 1, the departure time of the departure is 6, the arrival time is 6.
Table 2 resident trip chain generation and feature extraction table
| Residents ID | Household ID | Movable chain | Traveling out Chain | Basic output Chain | Go out of journey Time | Go to reach Time | Starting of return stroke Time | Return path to Time | Journey-going traffic (Mode) | Return traffic (Mode) | Starting traffic Cell | Arrival traffic Cell |
| 1 | 1 | HSHWSH | HSH | HSH | 633 | 650 | 756 | 810 | Private car self Driving device | Private car self Driving device | 1 | 1 |
| 2 | 1 | HSHWSH | HWSH | HWH | 845 | 858 | 2100 | 2110 | Private car self Driving device | Private car self Driving device | 1 | 1 |
| 3 | 1 | HSHWBS OH | HSH | HSH | 730 | 735 | 755 | 810 | Private car self Driving device | Private car self Driving device | 1 | 1 |
| 4 | 2 | HSHWBS OH | HWBS OH | HWH | 822 | 830 | 1930 | 1959 | Private car self Driving device | Private car self Driving device | 1 | 1 |
| 5 | 2 | HSOOHS HOH | HSOH | HSH | 617 | 628 | 1012 | 1030 | Electric vehicle | Walking device | 2 | 3 |
| 6 | 2 | HSOOHS HOH | HSH | HSH | 1121 | 1209 | 1221 | 1250 | Walking device | Walking device | 2 | 2 |
| 7 | 3 | HSOOHS HOH | HOH | HOH | 1522 | 1540 | 1619 | 1642 | Walking device | Walking device | 2 | 2 |
| 8 | 3 | HSWBHW H | HSWB H | HWH | 815 | 830 | 1046 | 1120 | Electric vehicle | Electric vehicle | 4 | 5 |
| 9 | 3 | HSWBHW H | HWH | HWH | 1243 | 1300 | 1630 | 1648 | Electric vehicle | Electric vehicle | 4 | 5 |
| 10 | 4 | HSHWSH | HSH | HSH | 630 | 645 | 705 | 715 | Electric vehicle | Electric vehicle | 8 | 9 |
| 11 | 4 | HSHWSH | HWSH | HWH | 830 | 840 | 1730 | 1740 | Electric vehicle | Electric vehicle | 10 | 11 |
| 12 | 5 | HSWBWB WSH | HSWS H | HWH | 1610 | 1630 | 2000 | 2010 | Private car | Private car | 12 | 13 |
| 13 | 5 | HSWBWB WSH | WBW | WBW | 1000 | 1010 | 1100 | 1110 | Private car | Private car | 13 | 14 |
| 14 | 5 | HSWBWB WSH | WBW | WBW | 1000 | 1010 | 1100 | 1110 | Private car | Private car | 13 | 14 |
The meanings of the keywords and abbreviations of the present invention are as follows:
a movable chain: and a chain is formed by sequentially connecting a series of activities of the traveler according to the sequence by taking 24 hours as a unit. An activity chain represents a series of trips that occur consistently by a resident that originate at a daily activity center (e.g., home, organization, school, etc.). Referring to fig. 2, a record of a person's travel activities throughout the day is represented.
And (4) going out of the chain: and starting from the starting point, after passing through a plurality of stopover points, finally returning to the series of travel combinations of the starting point. Thus, an activity chain may contain 1 or more trip chains, each of which contains multiple trips, such as home-unit-home, unit-business trip-unit, and so on. Travel, the trip chain and the activity chain are involved.
Basic trip chain: the method is used for analyzing and modeling trip chain characteristics after abstraction, merging and screening from the trip chain. The basic trip chain is a trip combination which starts from a starting point, only comprises 1 intermediate stop point on the way and finally returns to the starting point, and the basic trip chain and the trip chain are in a contained relation.
Half-way trip chain: for special reasons the trip chain cannot return to the starting point within 24 hours.
In embodiment 2, the computer device of the present invention may be a device including a processor and a memory, for example, a single chip microcomputer including a central processing unit. And the processor is used for implementing the steps of the recommendation method capable of modifying the relationship-driven recommendation data based on the CREO software when executing the computer program stored in the memory.
The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid state storage device.
Embodiment 3 computer-readable storage Medium embodiments
The computer readable storage medium of the present invention may be any form of storage medium that can be read by a processor of a computer device, including but not limited to non-volatile memory, ferroelectric memory, etc., and the computer readable storage medium has stored thereon a computer program that, when the computer program stored in the memory is read and executed by the processor of the computer device, can implement the above-mentioned steps of the CREO-based software that can modify the modeling method of the relationship-driven modeling data.
The computer program comprises computer program code which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The present invention has been disclosed in an illustrative rather than a restrictive sense, and the scope of the present invention is defined by the appended claims.
Claims (10)
1. A travel chain feature extraction method based on resident activities is characterized by comprising the following steps:
s1, acquiring urban resident trip survey data to obtain resident trip activity data;
s2, preprocessing resident trip activity data to obtain resident activity stay point data;
s3, traversing the stay point data of each resident, extracting the active chain of each resident all day, and writing the travel attribute feature information of each stay point into an active chain dictionary;
s4, traversing the activity chain of each resident all day, splitting the activity chain of each resident all day into a plurality of different resident trip chains, acquiring trip attribute information of the stay points corresponding to the activity chain all day, and writing the trip attribute information into a trip chain dictionary;
s5, traversing the travel chain of each resident, splitting the travel chain of each resident into resident basic travel chains, acquiring travel attribute information of a stop point corresponding to the basic travel chains, and writing the travel attribute information into a basic travel chain dictionary;
and S6, extracting the travel characteristic information of the resident travel chain according to the basic travel chain with the travel attribute information.
2. The method for extracting travel chain features based on resident activities according to claim 1, wherein the resident travel activity data includes resident ID, family ID, personal occupation type, order of stop point, longitude of stop point, latitude of stop point, departure time of stop point, arrival time of stop point, travel purpose of stop point, code of travel purpose of stop point, travel mode of stop point and start point of all day activity.
3. The method for extracting the travel chain features based on the activities of the residents according to claim 2, wherein the method for preprocessing the travel activity data of the residents is as follows: and matching the city traffic cell, administrative region and zone rejection stop point trip purpose with the empty resident trip record according to the longitude and latitude information of the resident activity stop point by combining the geographic information data of the city traffic cell.
4. The method for extracting the characteristics of the travel chain based on the activities of the residents according to claim 3, wherein the specific method S3 comprises the following steps: the method comprises the following steps:
s31, reading resident activity stop point data, grouping according to resident IDs, sequencing from morning to evening according to the time sequence of the resident activity stop points, and obtaining codes of travel starting points of residents all day;
s32, presetting codes of starting points of the resident activity chains as the travel starting points of the residents all day, traversing all activity stop points of the residents all day, sequentially linking the travel destination codes of the activity stop points to the resident activity chains, and splicing the travel destination codes with the travel destination codes of the stop points in the previous sequence;
and S33, after traversing all the resident activity stop point information, generating a resident activity chain and corresponding stop point travel attribute information, writing the resident activity chain and the corresponding stop point travel attribute information into an activity chain dictionary, and finishing the extraction of the resident activity chain all day.
5. The method for extracting the characteristics of the travel chain based on the activities of the residents according to claim 4, wherein the specific method of S4 is as follows: the method comprises the following steps:
s41, reading all resident activity chains and corresponding trip attribute information of the stop points;
s42, traversing the one-day activity chain and corresponding trip attribute information of each resident;
s43, splitting the active chain with the start end and the end as 'home' into 'home-home' trip chains, acquiring corresponding trip attribute information, and writing the trip attribute information into a trip chain dictionary;
s44, further splitting a working 'home-home' trip chain contained in the trip chain dictionary in the S42, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into the trip chain dictionary;
s45, directly reserving the active chains of which the starting and ending points of the active chains are not completely home, acquiring corresponding trip attribute information, and writing the corresponding trip attribute information into a trip chain dictionary;
and S46, after traversing all the resident activity chains, generating a resident trip chain and trip attribute information of a corresponding stop point, writing the resident trip chain and the trip attribute information into a trip chain dictionary, and finishing the extraction of the resident trip chain.
6. The method for extracting the characteristics of the travel chain based on the activities of the residents according to claim 5, wherein S43 comprises the following specific steps: the method comprises the following steps:
s431, reading a movable chain with a resident starting point and a resident ending point as 'home' and travel attribute information of a corresponding stop point;
s432, removing duplication of stop points continuously appearing in the active chain, and keeping the stop points appearing for the first time or the last time and travel attribute information;
s433, presetting an empty list corresponding to each active chain to be split into trip chains, circularly traversing the active chain stop points with the start terminal and the end terminal being H, sequentially reading stop point codes and corresponding trip attribute information,
s434, directly adding the stop point codes of the stop points, which are not home, in the middle of the active chain into the trip chain to be extracted, cutting off the positions, which are home, of the stop points in the middle of the active chain, extracting the trip chain of home, and correspondingly extracting the trip attribute information of the stop points corresponding to the trip chain;
s435, taking the cut-off stop point in S434 as the starting point of the next trip chain, and cutting off when meeting the stop point of 'home' until the terminal 'home' of the traversing active chain stops;
and S436, after traversing all resident activity chains, completing the separation of the activity chains according to the 'home-home' trip chain, acquiring the trip attribute information of the corresponding stop point, writing the attribute information into a trip chain dictionary, and completing the extraction of the resident 'home-home' trip chain.
7. The method for extracting the characteristics of the travel chain based on the activities of the residents according to claim 6, wherein S44 specifically comprises the following steps: the method comprises the following steps:
s441, reading a trip chain with the start and end points of residents as 'home' and trip attribute information of a corresponding stop point;
s442, traversing each travel chain of each resident, counting the number w _ num of 'working' stop points contained in the travel chain, if the w _ num is smaller than or equal to 1, directly keeping the original travel chain, and if the w _ num is larger than 1, executing the next step;
s443, extracting a position index start _ index of a first occurrence of a 'working' stop point in a trip chain and a position index end _ index of a last occurrence of the 'working' stop point as a cut-off position of trip chain splitting;
s444, further splitting the trip chain according to the index position of work in the trip chain, splitting the trip chain containing more than 3 stop points into a trip chain with a start point and an end point as home, wherein the middle stop point only contains the trip chain of home with the stop points of 1 work and the trip chain of work with the start point and the end point as work;
s445, further splitting the work/work trip chain with the starting point and the ending point of the work in the S444, and splitting the trip chain containing more than 2 work stop points into a plurality of work/work trip chains only containing 2 work/work stop points;
and S446, after traversing all resident trip chains, splitting the trip chain with the starting and ending points of ' home and ' work ' for the second round, and acquiring the trip attribute information of the corresponding stop point.
8. The method for extracting the characteristics of the travel chain based on the activities of the residents according to claim 7, wherein the specific method of S5 is as follows: the method comprises the following steps:
s51, reading a resident trip chain and trip attribute information of a corresponding stop point;
s52, presetting the priority of non-key stop points of the resident trip chain, and ensuring that the stop points with higher priority are reserved in the process of splitting the basic trip chain of residents by the resident trip chain;
s53, traversing each travel chain of each resident, and sequentially reading the stop point codes and the corresponding stop point travel attribute information in the travel chains;
s54, splitting non-key stay points in the 'home' trip chain, traversing the stay points with preset priorities according to the priority order aiming at the 'home' trip chain, judging whether the trip chain comprises the corresponding stay points, and if the trip chain comprises the corresponding stay points, extracting a basic trip chain comprising the corresponding stay points;
s55, splitting non-key stop points in the 'working-on' trip chain, traversing the stop points with preset priorities according to the priority order of the 'working-on' trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
s56, splitting non-key stop points in the 'home' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'home' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
s57, splitting non-key stop points in the 'working-start' half trip chain, traversing the stop points with preset priorities according to the priority order of the 'working-start' half trip chain, judging whether the trip chain comprises corresponding stop points, and extracting a basic trip chain comprising the corresponding stop points if the trip chain comprises the corresponding stop points;
and S58, after traversing all resident trip chains, splitting the resident trip chain to finish the basic trip chain, acquiring the trip attribute information of the corresponding stop point, writing the attribute information into a basic trip chain dictionary, and finishing the extraction of the resident basic trip chain.
9. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the resident activity based travel chain feature extraction method according to any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium on which a computer program is stored, the computer program, when being executed by a processor, implementing a resident activity based travel chain feature extraction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310096115.4A CN115827643B (en) | 2023-02-10 | 2023-02-10 | Travel chain feature extraction method based on resident activities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310096115.4A CN115827643B (en) | 2023-02-10 | 2023-02-10 | Travel chain feature extraction method based on resident activities |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115827643A true CN115827643A (en) | 2023-03-21 |
| CN115827643B CN115827643B (en) | 2023-05-16 |
Family
ID=85520982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310096115.4A Active CN115827643B (en) | 2023-02-10 | 2023-02-10 | Travel chain feature extraction method based on resident activities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115827643B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144030A1 (en) * | 2003-12-01 | 2005-06-30 | Mazza Vincent D. | System and method for territory based commission attribution |
| CN104731853A (en) * | 2014-12-18 | 2015-06-24 | 东南大学 | Public transport passenger flow spatial and temporal distribution simulation method and simulation system based on individual activity chain |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| CN105513351A (en) * | 2015-12-17 | 2016-04-20 | 北京亚信蓝涛科技有限公司 | Traffic travel characteristic data extraction method based on big data |
-
2023
- 2023-02-10 CN CN202310096115.4A patent/CN115827643B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050144030A1 (en) * | 2003-12-01 | 2005-06-30 | Mazza Vincent D. | System and method for territory based commission attribution |
| CN104731853A (en) * | 2014-12-18 | 2015-06-24 | 东南大学 | Public transport passenger flow spatial and temporal distribution simulation method and simulation system based on individual activity chain |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| CN105513351A (en) * | 2015-12-17 | 2016-04-20 | 北京亚信蓝涛科技有限公司 | Traffic travel characteristic data extraction method based on big data |
Non-Patent Citations (2)
| Title |
|---|
| 佘世英等: "基于集计出行链的城市交通模型架构研究" * |
| 郑猛等: "大城市交通出行链模型发展路径辨识 ——以武汉为例" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115827643B (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lang | Office sprawl: The evolving geography of business | |
| Inskeep | Tourism planning: An integrated and sustainable development approach | |
| CN105677793A (en) | Site database establishing method and device, and candidate riding site recommending method and device | |
| CN113034251A (en) | Online bidding management system | |
| CN110147923A (en) | The method and device of risk subscribers for identification | |
| CN113052505A (en) | Cross-border travel recommendation method, device and equipment based on artificial intelligence | |
| Letdin et al. | Location choice, life cycle and amenities | |
| CN115827643A (en) | Travel chain feature extraction method based on resident activities | |
| Stopher et al. | Comparing GPS and prompted recall data records | |
| Nel et al. | The identification of possible future provincial boundaries for South Africa based on an intramax analysis of journey-to-work data | |
| CN102945267A (en) | Method for processing ticket business transaction data in track traffic | |
| Nasiboglu et al. | Origin-destination matrix generation using smart card data: Case study for Izmir | |
| Ibrahim et al. | Identification and analysis of land use change in Doha downtown neighborhoods | |
| Kumar et al. | Folksomaps-towards community driven intelligent maps for developing regions | |
| Azhar et al. | Local Government Efforts to Attract Tourists to Silokek Geopark Tourism | |
| KR20200077288A (en) | System for auto making of tour plan | |
| CN109781130A (en) | The method and apparatus that bus route is planned automatically | |
| Hashiguchi et al. | Productivity and human capital agglomeration: evidence from indonesian cities | |
| Sepehri et al. | Designing a mobile application for tourism in the architectural heritage of Tehran | |
| Higgins | Changing Tides: A Review of Cape Cod’s Suburbanization and Its Suitability for MBTA Commuter Rail Service | |
| Darumurti et al. | Digital Tourism Branding in Post-Pandemic Covid-19 based on the Agile Governance Concept in Pacitan Regency | |
| CN112990875A (en) | Integrated method, system, terminal equipment and storage medium for importing whole process project resources | |
| Lovro | A branch and bound algorithm applied to field office location | |
| US20220076369A1 (en) | Self-learning based mechanism for vehicle utilization and optimization | |
| CN114780670A (en) | Travel purpose-based driver travel mode mining method and system |
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 |