CN117056823A - Method and system for identifying occupation type of shared bicycle commuter user - Google Patents
Method and system for identifying occupation type of shared bicycle commuter user Download PDFInfo
- Publication number
- CN117056823A CN117056823A CN202310910372.7A CN202310910372A CN117056823A CN 117056823 A CN117056823 A CN 117056823A CN 202310910372 A CN202310910372 A CN 202310910372A CN 117056823 A CN117056823 A CN 117056823A
- Authority
- CN
- China
- Prior art keywords
- user
- data
- shared bicycle
- riding
- bicycle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012216 screening Methods 0.000 claims abstract description 47
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000010606 normalization Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 4
- 230000005484 gravity Effects 0.000 claims description 31
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000011835 investigation Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000007726 management method Methods 0.000 abstract description 5
- 238000011160 research Methods 0.000 description 9
- 239000000872 buffer Substances 0.000 description 6
- 230000006399 behavior Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000009304 pastoral farming Methods 0.000 description 3
- 239000008186 active pharmaceutical agent Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000005441 aurora Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for identifying occupation types of shared bicycle commuting users, which relate to the fields of traffic management technology and city planning and comprise the following steps: receiving POI data, urban road network data and shared bicycle data, and processing to obtain shared bicycle effective data; calculating the normalization parameters of the user using the shared bicycle in the early peak of the working day of the week, and carrying out primary screening extraction on the effective data of the shared bicycle to obtain primary effective data of the shared bicycle; performing secondary screening extraction on the primary sharing bicycle effective data in the time dimension to obtain secondary sharing bicycle effective data; carrying out three-time screening extraction on the effective data of the secondary sharing bicycle in the space dimension to obtain the effective data of the tertiary sharing bicycle; determining a decision area of the occupation type of the user according to the maximum walking radius and combining the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area.
Description
Technical Field
The invention relates to the fields of traffic management technology and city planning, in particular to a method and a system for identifying occupation types of shared bicycle commuter users.
Background
The commuter travel is one of basic activities in daily living of residents, and the community attribute of the residents is combined to discuss the difference of the commuter travel time-space law of different types of groups, so that the fine study on the crowd-space behavior law is facilitated, the differentiation mechanism of the human-ground interaction is dug, the supply of corresponding systems of the city is purposefully improved, and the habitable city is built with high quality. With popularization of sharing economy and perfection and application of related technologies such as internet communication technology, GNSS (GlobalNavigationSatelliteSystem) positioning technology and satellite remote sensing, the sharing bicycle becomes the optimal choice for short-distance travel and public transportation by means of high convenience and high economy. According to the aurora data of 2017, china middle and small city shared bicycle development report, the purpose of using the shared bicycle and the specific gravity thereof are as follows: commute to work and from work (26.4%), shopping (25.4%), sports (23.3%), scenic spot travel (11.4%), school (10.5%), others (2.9%). It can be seen that the sharing bicycle has become one of important public transportation means for residents to complete commute activities, so that exploring the space-time rules of the sharing bicycle from the view of social attribute diversity has important value significance as well: the intelligent traffic management system is beneficial to understanding behavior geography and time geography deeply from a social perspective, promoting the research of related theoretical models, optimizing and adjusting urban space structures and functional compartments, improving the supply of urban traffic systems, constructing intelligent traffic management systems and the like.
Social attributes of shared bicycle users typically include age, gender, educational level, occupation type, income level, etc., where occupation type is the most closely related to commuter travel, but such data is not only difficult to obtain directly through web crawling, but also easily ignored even when data is missed and subsidized through questionnaire sampling. In terms of feasibility of sharing the professional type recognition of the bicycle users, on one hand, the professional types of most users are basically matched with the work sites of the users; on the other hand, the spatial information and properties of the work site can be reflected by the industry field of the POI; in addition, the working place is closely related to the land property and the functional structure of the city, and the distribution point of the sharing bicycle is often closely related to the land function of the city (for example, more sharing bicycles are usually put in a high-new industry park, an office area and the like to match supply and demand), so that a practical basis and a practical operation possibility are provided for the occupation type identification of big data samples of the sharing bicycle commuting users. In short, as one of the few social attributes obtained by data calculation, professional type identification methods still have a study blank and are closely related to commuter trips with great influence on urban space; more importantly, similar researches in the past often stay in a rough description of an overall state, but deep rules cannot be finely excavated.
At present, research on shared bicycles at home and abroad mainly focuses on riding paths, hot spot area identification and the like, and research on user occupation type identification methods is less. From the aspect of research content, the user occupation type recognition method can be used for reference research and mainly focused on recognition of travel purposes, the user activity type and space-time mode are explored according to the method through POI matching and other modes, from the aspect of technical methods, mobile phone signaling data, POI data, AOI (AreaofInterest) data, TUD (Technical UniversityofDortmund) data, urban road network data and the like are combined, bayesian rules, gravity models, DMR models, K nearest neighbor and other models are adopted for predicting a sharing bicycle destination, and students adopt a K-means++ clustering method based on the sharing bicycle data and the POI data to study the sharing bicycle travel mode and travel purposes, so that the method has the following problems in the general view: (1) In research content, the method mainly focuses on space-time aspects and travel purposes, lacks attention to social attributes such as age, gender, education level, occupation type, income level and the like of a user main body, and particularly has the social attribute of the occupation type, which is most closely related to commuter travel, is difficult to directly acquire by utilizing a web crawler and is also easy to ignore in sampling questionnaire survey; (2) In the technical method, the consideration of the actual complex situation is insufficient, and the space-time difference of the characteristics of the resident commuting behaviors of different occupation types is ignored; meanwhile, a single riding terminal point is utilized to search a corresponding destination, and the randomness of the parking of the shared bicycle and errors caused by network delay are not considered, so that high accuracy is difficult to ensure in the identification of large sample data.
Disclosure of Invention
In order to solve the above-mentioned shortcomings in the background art, an object of the present invention is to provide a method and a system for identifying occupation types of shared bicycle commuter users.
The aim of the invention can be achieved by the following technical scheme: a method of identifying occupation types of shared bicycle commuter users, the method comprising the steps of:
receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
calculating the normalization parameters of the user using the shared bicycle in the early peak of the week, and carrying out primary screening extraction on the effective data of the shared bicycle by utilizing the normalization parameters of the user using the shared bicycle in the early peak of the week to obtain primary effective data of the shared bicycle;
counting accumulated days of the user using the shared bicycle in the working days of the week, and performing secondary screening extraction on the effective data of the primary shared bicycle in the time dimension to obtain the effective data of the secondary shared bicycle;
counting the end position of the shared bicycle used by the user on the working day of the week, and carrying out three-time screening and extraction on the effective data of the secondary shared bicycle in the space dimension to obtain the effective data of the tertiary shared bicycle;
determining a decision area of the occupation type of the user by utilizing the maximum walking radius and the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area of the occupation type of the user.
Preferably, the information of the shared bicycle data includes an order number, a user number, a vehicle number, a time of starting and ending riding, and geographical coordinates of a riding track.
Preferably, the cleaning and screening are performed on the shared bicycle data, so that the shared bicycle data with the riding time not more than 1h and the average riding speed in the interval of 1km/h-30km/h is the shared bicycle effective data.
Preferably, the user's use of the shared bicycle at an early weekday peak's normalization parameters includes calculating a maximum tolerable walking distance threshold from the departure point to the pick-up point/riding start point and identifying an early peak period.
The basis and the method are as follows:
since the endpoints of commuter travel are typically living places and work places, and the riding start points generally comprise three possible places, namely living places (whole-course use), buses or subways (transfer use), in combination with the daily commuter use mode of sharing the bicycle. As known from the related research reports, the shared bicycle mainly replaces the walking traffic, but the substitution capability for public traffic is limited, and the behavior of connecting subways by using the bicycle is wider than that of buses. Therefore, the order of shared bicycle data extraction is subway station entrance→bus station→residence. Respectively by r M 、r B And r H Multiple ring buffers are created for base units for subway station exits, bus stops, and residential buildings of open cells (or exits of closed cells). The frequency of sharing the starting point of riding the bicycle within each buffer loop is then counted. The distance corresponding to the inflection point of the frequency change of the starting point of the shared bicycle riding in the buffer ring is taken as a threshold value (R M 、R B 、R H )。
Since the morning commute typically has a time limit of checking in a card, and the time available to the user after work increases, the purpose of sharing a single trip in the evening is more diversified and complex than in the morning. Accordingly, the shared bicycle data of the early peak period can reflect the commute service condition of the shared bicycle more than the shared bicycle data of the early peak period. From life experience, the usual early Gao Fengtong duty period of the workday is determined to be 07:00-10:00. And extracting valid data of the shared bicycle order starting time in the period.
Preferably, the process of performing the secondary screening extraction on the primary sharing bicycle valid data in the time dimension is as follows:
and (3) taking the user with the number of days of the shared bicycle being more than or equal to 3 days in the working days of five days of a week as an effective user, judging that the corresponding effective data of the shared bicycle is effective, setting the accumulated number of days of the shared bicycle being used in the working days of five days of a week as t, and judging:
if t is less than or equal to 2, rejecting the corresponding one-time sharing bicycle effective data;
and if t >2, extracting the corresponding primary sharing bicycle effective data and marking the primary sharing bicycle effective data as the secondary sharing bicycle effective data.
The basis is that the number of days of work for a user's week is typically at least 3 days (i.e., 3 shift production workers, except free workers). Accordingly, usage data of the shared bicycle should be recorded for at least 3 days and more during 5 days of the week. Therefore, the user with the sharing bicycle use days more than or equal to 3 days is taken as the effective user, and the corresponding sharing bicycle use data is taken as the effective data.
Preferably, the third filtering and extracting are performed on the effective data of the secondary sharing bicycle in the space dimension according to the following steps: firstly, considering the randomness of a user for parking a shared bicycle in real life, it is difficult to ensure that the user parks the shared bicycle at the same position (the same geographic coordinate) accurately every day, so that riding terminals repeatedly appearing in a week of the shared bicycle should be gathered in a certain space range, namely all possible riding terminal groups of a certain destination are formed; secondly, the commuter's working place is fixed, so the space position (geographic coordinate) of the riding end point of the shared bicycle should repeatedly appear on different workdays marked with dates; thirdly, during the working day, users use the shared bicycle to carry out commuter travel, and compared with other travel purposes, the shared bicycle has stronger rigidity requirement, so the number of riding endpoints in the effective clustering group is the largest. The method comprises the following specific steps:
identifying and classifying all possible riding terminal point data of a certain destination of any effective user, calculating the distances between all the riding terminal points of the user by using space coordinate data for any user, performing cluster analysis by taking the distances as parameters, and outputting all possible riding terminal point position data of each destination of any user;
if the number of different date labels in all possible riding endpoint data of a certain destination of any effective user exceeds half of the accumulated use days of the user, the destination is used as one of possible candidate working sites of the user;
identifying the candidate working place with the largest amount of possible riding terminal data as the most possible working place, counting the amount of the riding terminal data contained in the possible working place of the user and all the possible riding terminal data of the user, extracting the destination with the largest riding terminal amount as the most possible working place of the user, extracting the corresponding effective data of the secondary sharing bicycle and marking the effective data as the effective data of the tertiary sharing bicycle.
Preferably, if the number of possible working places and all possible riding endpoints of the user have a plurality of identical maximum values, comparing the sum of distances between every two corresponding all possible riding endpoints of the candidate working places, and taking the candidate working place with the smallest sum of distances as the most probable working place of the user.
Preferably, the defining process of the professional type decision area of the user is as follows:
calculating the maximum tolerable walking distance r (maximum walking radius) from the parking point/riding end point D to the destination, calculating the distance between the riding end point of the shared bicycle and the nearest neighbor POI data around the riding end point, drawing a maximum walking radius-shared bicycle data volume ratio histogram, and adaptively determining the value of the maximum tolerable walking distance from the parking point/riding end point to the destination, wherein the following two conditions are simultaneously satisfied:
in a circular area taking a riding end point of the shared bicycle as a circle center and r as a radius, at least 1POI data can be inquired;
the shared bicycle data satisfying the above condition accounts for 90% of the total shared bicycle data;
for all possible riding endpoints of any most likely working place, taking one riding endpoint as a center, taking the maximum tolerable walking distance r from a parking point/riding endpoint D to a destination as a radius, calculating a walking reachable range based on an actual road network, and then fusing the walking reachable ranges of all the riding endpoints to be a decision area A of the occupation type of a shared bicycle user d 。
Preferably, the method for establishing the correspondence between the POI data and the occupation type comprises the following steps:
the industry field classification of the Goldmap POI data is compared with the national standard of the people's republic of China, occupation classification and code (GB/T6565-2009), so that the occupation type of the user can be accurately identified. The determined occupation types comprise professional technicians, clerks and related personnel, business service personnel, production and transportation equipment operators and related personnel, and 5 kinds of production personnel for agriculture, forestry, grazing, fishing and aquatic products.
Preferably, the process of identifying the occupation type of the user is as follows:
combining a basic formula of a gravity model, comprehensively considering factors influencing the occupation type of a user, and determining variables involved in operation, including distance, type specific gravity and environment, wherein the distance is calculated in a decision area A d Average distance between a certain POI and each riding endpoint in any effective cluster group; the calculation mode of the type proportion is decision area A d The ratio of the number of POIs mapped to a certain professional type to the number of POIs mapped to that professional type throughout the investigation region; the computing mode of the environment is decision area A d The ratio of any one of the occupational type gravities to the sum of the 5 occupational type gravities is as follows:
wherein t is ij For P i And P j Population, d, of cells i and j, respectively ij The distance between the cells i and j is given, and k is a model parameter; ρ is the type specific gravity, number (importation) i ) For the number of POIs mapped to a certain professional type in a decision area of a certain user, sum (occupancy) i ) Mapping the number of POIs of the occupation type to the whole decision area; c is an environmental parameter ρ i For a type specific gravity of a certain professional type in a decision area of a certain user,a type specific gravity sum of 5 occupation types in a decision area of a certain user;
the method comprises the steps that the effective sharing riding terminal data of a certain user is combined with POI data, and the probability that the user is a professional technician, a clerk and related personnel, a business service personnel, a production and transportation equipment operator and related personnel, a agriculture, forestry, grazing, fishing and aquatic product production personnel is measured one by using a gravity model; and calculating the normalization probability of the user for the job types by using a Bayesian rule, taking the job type corresponding to the highest value of the normalization probability as the job type of the user, and outputting a recognition result, wherein the formula is as follows:
wherein GD, P i For the probability that a user is of a certain professional type,an average distance between a POI and all possible riding endpoints most likely to be destination at the work site within a user's decision area; p (P) r P i D is the normalized probability that a user is of a professional type,/-for>The probability sum of 5 occupation types for a certain user respectively;
if the normalized probability of 2 or more occupation types of a certain user is the same, comparing the absolute values of single parameters according to the sequence of distance, type proportion and environment, taking the occupation type with the largest absolute value as the final occupation type of the user, namely when the maximum value of the distance parameters of 2 or more occupation types is the same, comparing the absolute values of the type proportion parameters, and the like.
In a second aspect, to achieve the above object, the present invention discloses a system for identifying occupation types of shared bicycle commuter users, comprising:
and a data processing module: the method comprises the steps of receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
and a primary screening module: the method comprises the steps of calculating a normalization parameter of a user using the shared bicycle in a weekday peak, and carrying out primary screening extraction on effective data of the shared bicycle by using the normalization parameter of the user using the shared bicycle in the weekday peak to obtain primary effective data of the shared bicycle;
and a secondary screening module: the method comprises the steps of counting accumulated days of a user using a shared bicycle in a working day of a week, and carrying out secondary screening extraction on effective data of a primary shared bicycle in a time dimension to obtain effective data of a secondary shared bicycle;
and a third screening module: the method comprises the steps that the method is used for counting the end position of a shared bicycle used by a user on a week working day, and carrying out three-time screening extraction on effective data of a secondary shared bicycle in a space dimension to obtain effective data of the tertiary shared bicycle;
and an identification module: and the method is used for determining a decision area of the occupation type of the user according to the maximum walking radius and combining the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area of the occupation type of the user.
The invention has the beneficial effects that:
the present invention provides a method for relatively accurately identifying the type of occupation of a user using shared bicycle commutes using multi-source LBS data. Firstly, determining a maximum tolerable walking distance threshold from a departure point to a pick-up point/a riding starting point (O) on the basis of primary screening data, identifying an early peak period, and primarily screening shared bicycle data of commuter travel; secondly, extracting effective working places and all possible riding terminal data thereof through operations such as date marking, library sorting and screening, further screening shared bicycle data of commuter travel, fusing all service areas taking the effective riding terminal as a circle center and the maximum tolerable walking distance from a parking point/riding terminal (D) to a destination as a radius on the basis, and generating a decision area for judging the occupation type of a user; then, establishing a mapping relation between the POI industry field and the occupation type; finally, a user occupation type using shared bicycle commutes is identified based on the gravity model and bayesian rules. The invention can conveniently and accurately judge the occupation type of the user using the shared bicycle commute, and provides a basis for researching the space-time laws of different travel activities of the shared bicycle, thereby further optimizing the shared bicycle scheduling management of specific space and the planning layout of related supporting facilities in specific time periods and providing powerful technical support for the efficient utilization of urban space and the reasonable allocation of urban resources.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to those skilled in the art that other drawings can be obtained according to these drawings without inventive effort;
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic of the workflow of the present invention;
FIG. 3 is a "maximum tolerable walking distance-shared bicycle data frequency" line diagram of the MYXC street of NJ city of the present invention from subway station entrances and exits, bus stops, and residence to pick-up points;
FIG. 4 is a "maximum walking radius-shared bicycle data volume duty" histogram for MYXC street in NJ city of the present invention;
FIG. 5 is a schematic diagram of a decision area for valid user occupation type identification for a certain sharing bicycle on MYXC street in NJ;
fig. 6 is a schematic diagram of the system structure of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a method for identifying occupation type of shared bicycle commuter includes the steps of:
receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
the method includes the steps that information of shared bicycle data comprises order numbers, user numbers, vehicle numbers, time for starting and ending riding and geographical coordinates of riding tracks, and then effective data of the shared bicycle are cleaned and screened, namely, data with riding time not more than 1h and average riding speed in a range of 1km/h-30km/h are used as the effective data, and abnormal data generated due to GNSS positioning offset of the shared bicycle, forgetting locking of the bicycle by a user and the like are removed;
in this embodiment, obtaining POI data of the MYXC street 2020 in NJ city, urban road network data, and usage data of the shared bicycle 2020, 2 months, 10 days (monday) and 14 days (friday) from a third party company (including order number, vehicle number, user number, order start and end time, and riding track data of the shared bicycle), primarily cleaning and screening the effective data of the shared bicycle, that is, extracting and retaining the data with riding time not more than 1h and average riding speed in the interval of 1km/h-30km/h, and participating in subsequent calculation;
calculating the normalization parameters of the user using the shared bicycle in the early peak of the week, and carrying out primary screening extraction on the effective data of the shared bicycle by utilizing the normalization parameters of the user using the shared bicycle in the early peak of the week to obtain primary effective data of the shared bicycle;
a maximum tolerable walking distance threshold is calculated from the departure point to the pick-up point/riding start point (O). Since the endpoints of commuter travel are typically living places and work places, and the riding start points generally comprise three possible places, namely living places (whole-course use), buses or subways (transfer use), in combination with the daily commuter use mode of sharing the bicycle. As known from the related research reports, the shared bicycle mainly replaces the walking traffic, but the substitution capability for public traffic is limited, and the behavior of connecting subways by using the bicycle is wider than that of buses. Therefore, the order of shared bicycle data extraction is subway station entrance→bus station→residence. Respectively by r M 、r B And r H Multiple ring buffers are created for base units for subway station exits, bus stops, and residential buildings of open cells (or exits of closed cells). The frequency of sharing the starting point of riding the bicycle within each buffer loop is then counted. The distance corresponding to the inflection point of the frequency change of the starting point of the shared bicycle riding in the buffer ring is taken as a threshold value (R M 、R B 、R H ) Effective data of the shared bicycle are sequentially extracted (taking MYXC streets of NJ city as an example, r are respectively taken as examples M ＝200m、r B =100m and r H =50m is the basic unit, and the maximum tolerable walking distance thresholds identifying the subway station doorway, bus station and residence to the pick-up point are 600m, 200m and 100m, respectively, see fig. 2).
Early rush hour is identified. Since the morning commute typically has a time limit of checking in a card, and the time available to the user after work increases, the purpose of sharing a single trip in the evening is more diversified and complex than in the morning. Accordingly, the shared bicycle data of the early peak period can reflect the commute service condition of the shared bicycle more than the shared bicycle data of the early peak period. From life experience, the usual early Gao Fengtong duty period of the workday is determined to be 07:00-10:00. And extracting valid data of the shared bicycle order starting time in the period.
Counting accumulated days of the user using the shared bicycle in the working days of the week, and performing secondary screening extraction on the effective data of the primary shared bicycle in the time dimension to obtain the effective data of the secondary shared bicycle;
any user is selected and each shared bicycle usage data for each of his 5 day of the week is dated (e.g., mon, tue, wed, thu, fri).
Typically, the number of days of operation for a user's week is at least 3 days (i.e., 3 shift production workers, except free workers). Accordingly, usage data of the shared bicycle should be recorded for at least 3 days and more during 5 days of the week. Therefore, the user with the sharing bicycle use days more than or equal to 3 days is taken as the effective user, and the corresponding sharing bicycle use data is taken as the effective data.
Specifically, counting the accumulated days (t) of using the shared bicycle on the working days of 5 days of the week of any user, wherein the dates of using the shared bicycle can be discontinuous and the serial numbers of the shared bicycle can be different; then traversing all users and classifying and building a library,
if t is less than or equal to 2, rejecting the user and the use data of the shared bicycle;
if t=3 or t=4, the usage data of the user and the shared bicycle are included in the database 1 (DS 1);
if t=5, the user and the shared bicycle use data are included in the database 2 (DS 2);
counting the end position of the shared bicycle used by the user on the working day of the week, and carrying out three-time screening and extraction on the effective data of the secondary shared bicycle in the space dimension to obtain the effective data of the tertiary shared bicycle;
it should be noted that, based on the distance clustering, all possible riding endpoint data of a certain destination of any effective user is identified and categorized. And calculating the distances (projection distances) between every two of all riding endpoints of any user of DS1 and DS2 by using the space coordinate data, performing Cluster analysis by taking the distances as parameters, and outputting a dataset { Cluster }, namely all possible riding endpoint position data of each destination of any user. The output result formed by sharing the usage data of the bicycle by all users in DS1 is { Cluster 1 }＝{{C 11 },{C 12 },…{C 1i And so on, the output result formed by the data of DS 2.
If the number of different date labels in all the possible riding endpoint data of a certain destination of any effective user exceeds half of the accumulated number of days of use of the user, the destination is used as one of possible candidate working sites of the user. This step aims at screening and extracting possible work sites for the user and related riding data. Specifically:
all possible riding endpoint data { C for any user's destination in DS1 1i Counting the number of different date labels (n 1i ) Reserve n 1i Data of more than or equal to 2 and corresponding user numbers thereof form a data set { Cluster } 1 '}＝{{C 11 '},{C 12 '},…{C 1i '}}；
All possible riding endpoint data { C for any user's destination in DS2 2i Counting the number of different date labels (n 2i ) Reserve n 2i Cluster group data not less than 3 and corresponding user numbers thereof to form a data set { Cluster } 2 '}＝{{C 21 '},{C 22 '},…{C 2i '}}。
And identifying all candidate working sites with the highest possible riding endpoint data as the most possible working sites. For { Cluster } 1 Any one of the sets { C }, C 1i ' statistics of the possible workplace of the user and all the possible riding end point data thereofNumber of riding endpoint data N, form { N 1 }＝{N 11 ,N 12 ,…N 1i }. For { N 1 All elements in the sequence are compared pairwise, and the { N } is searched 1 Maximum value of elements in (i.e. the maximum number of riding terminal points) and corresponding { C 1i ' is identified as all riding endpoint valid data most likely to be destined for the work site. Similarly, for { Cluster } 2 ' the same operation is performed.
In particular, if the user's possible work place and the number of all possible riding stops are the same (i.e., { N 1 Or { N } 2 2 or more maximum values of elements in the user's map are found), the sum of the distances between every two corresponding possible riding endpoints of the candidate working sites is compared, the candidate working site with the smallest sum of the distances is used as the most likely working site of the user, and relevant data (user number, all associated riding endpoint data and the like) are extracted.
The decision area of the user's occupation type is determined using the maximum walking radius and the urban road network data, and it is to be noted that in the present embodiment, the maximum tolerable walking distance from the parking spot/riding end point (D) to the destination is calculated. Because of the relative flexibility of parking a pile-free shared bicycle, users prefer to park the shared bicycle in an electronic fence near the destination. Based on this, the maximum tolerable walking distance from the shared bicycle riding end point (parking point) to the destination, which is tolerable by the user, is taken as the maximum walking radius (r). By calculating the distance between the riding end point of the shared bicycle and the nearest neighbor POI data around the riding end point, and drawing a histogram of the maximum walking radius and the shared bicycle data volume ratio (the specific gravity change of the shared bicycle data volume of at least 1POI in the total shared bicycle data volume can be searched in a certain range), the specific value of the maximum walking radius is adaptively determined, and the following two conditions are simultaneously satisfied: firstly, in a circular area taking a riding end point of a shared bicycle as a circle center and r as a radius, at least 1POI data can be inquired; secondly, the specific gravity of the shared bicycle data in the total shared bicycle data is 90% (note that the measurement result of the maximum walking radius varies with the ground, and the maximum walking radius r=100m is calculated by taking the MYXC street in NJ city as an example, see fig. 3).
For all possible riding endpoints of any most likely working place, taking one riding endpoint as a center and taking the maximum tolerable walking distance (r) from a parking point/riding endpoint (D) to a destination as a radius, calculating a walking reachable range based on an actual road network, and then fusing the walking reachable ranges of all the riding endpoints to be used as a decision area A of the occupation type of the sharing bicycle user d (see FIG. 4).
The corresponding relation between POI data and occupation type is judged as shown in table 1:
table 1 correspondence table of industry field classifications and occupation types for POI
And identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining with the decision area of the occupation type of the user.
S1, determining a variable participating in operation and a calculation method thereof. In combination with the basic formula (Eq.1) of the gravity model, factors which possibly affect the occupation type of the user are comprehensively considered, and variables involved in operation including distance (d), type specific gravity (ρ) and environment (C) are determined. Wherein the distance is calculated by a decision area (A d ) Average distance between a POI and each riding endpoint in any active cluster groupThe type specific gravity is calculated by a decision area (A d ) Is mapped to the number of POIs of a certain occupation type (number (occupation) i ) And the number of POIs (occupation) mapped to the occupation type over the entire investigation region ( i ) Ratio (eq.2); the environment is calculated as a decision area (A d ) Specific gravity of any one of the occupation types and ratio of 5 kinds of occupation typesThe ratio of the sum of the weights (Eq.3). The correlation formula is as follows:
wherein t is ij For P i And P j Population, d, of cells i and j, respectively ij The distance between the cells i and j is given, and k is a model parameter; ρ is the type specific gravity, number (importation) i ) For the number of POIs mapped to a certain professional type in a decision area of a certain user, sum (occupancy) i ) Mapping the number of POIs of the professional type to the entire investigation region; c is an environmental parameter ρ i For a type specific gravity of a certain professional type in a decision area of a certain user,is the sum of the type specific gravity of 5 professional types in the decision area of a certain user.
S2: the method comprises the steps that the effective sharing riding terminal data of a certain user is combined with POI data, and the probability of the user being a professional technician, a clerk and related personnel, a business service personnel, a production and transportation equipment operator and related personnel, a agriculture, forestry, grazing, fishing and aquatic product production personnel is measured one by using a gravity model (Eq.4); and calculating the normalized probability (Eq.5) of the user as the job type by using a Bayesian rule, taking the job type corresponding to the highest value of the normalized probability as the job type of the user, and outputting an identification result. The correlation formula is as follows:
wherein GD, P i For the probability that a user is of a certain professional type,an average distance between a POI and all possible riding endpoints most likely to be destination at the work site within a user's decision area; p (P) r P i D is the normalized probability that a user is of a professional type,/-for>The sum of probabilities of 5 occupation types for a certain user is provided.
In particular, if a user has 2 or more occupation types with the same normalized probability, the user is determined by distanceThe absolute values of the single parameters are compared in the order of the type specific gravity (ρ) and the environment (C), and the occupation type with the largest absolute value is taken as the final occupation type of the user. I.e. when 2 or more occupational type distance parameters are the same maximum value, the absolute values of the type specific gravity parameters are compared, and so on.
The judging result is verified by field observation and interview residents around a certain office area of MYXC street in NJ city, the accuracy rate can reach 67.9%, and the necessity and the effectiveness of the method are proved.
In a second aspect, to achieve the above object, as shown in fig. 6, the present invention discloses a system for identifying occupation types of shared bicycle commuter users, comprising:
and a data processing module: the method comprises the steps of receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
and a primary screening module: the method comprises the steps of calculating a normalization parameter of a user using the shared bicycle in a weekday peak, and carrying out primary screening extraction on effective data of the shared bicycle by using the normalization parameter of the user using the shared bicycle in the weekday peak to obtain primary effective data of the shared bicycle;
and a secondary screening module: the method comprises the steps of counting accumulated days of a user using a shared bicycle in a working day of a week, and carrying out secondary screening extraction on effective data of a primary shared bicycle in a time dimension to obtain effective data of a secondary shared bicycle;
and a third screening module: the method comprises the steps that the method is used for counting the end position of a shared bicycle used by a user on a week working day, and carrying out three-time screening extraction on effective data of a secondary shared bicycle in a space dimension to obtain effective data of the tertiary shared bicycle;
and an identification module: and the method is used for determining a decision area of the occupation type of the user according to the maximum walking radius and combining the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area of the occupation type of the user.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing has shown and described the basic principles, principal features, and advantages of the present disclosure. It will be understood by those skilled in the art that the present disclosure is not limited to the embodiments described above, which have been described in the foregoing and description merely illustrates the principles of the disclosure, and that various changes and modifications may be made therein without departing from the spirit and scope of the disclosure, which is defined in the appended claims.
Claims (10)
1. A method of identifying occupation types of shared bicycle commuter users, the method comprising the steps of:
receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
calculating the normalization parameters of the user using the shared bicycle in the early peak of the week, and carrying out primary screening extraction on the effective data of the shared bicycle by utilizing the normalization parameters of the user using the shared bicycle in the early peak of the week to obtain primary effective data of the shared bicycle;
counting accumulated days of the user using the shared bicycle in the working days of the week, and performing secondary screening extraction on the effective data of the primary shared bicycle in the time dimension to obtain the effective data of the secondary shared bicycle;
counting the end position of the shared bicycle used by the user on the working day of the week, and carrying out three-time screening and extraction on the effective data of the secondary shared bicycle in the space dimension to obtain the effective data of the tertiary shared bicycle;
determining a decision area of the occupation type of the user according to the maximum walking radius and combining the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area of the occupation type of the user.
2. The method of claim 1, wherein the information of the shared bicycle data includes order number, user number, vehicle number, time of start and end of riding, geographical coordinates of riding track.
3. The method for identifying occupation type of shared bicycle commuter user according to claim 1, wherein the cleaning and screening are performed on the shared bicycle data to make the shared bicycle effective data with riding time not more than 1h and average riding speed in the range of 1km/h-30 km/h.
4. The method of identifying a shared bicycle commuter user occupation type of claim 1 wherein the user's use of the shared bicycle at an early weekday peak normalized parameter includes calculating a maximum tolerable walking distance threshold from a departure point to a pick-up point/a riding start point and identifying an early peak period.
5. The method for identifying occupation type of sharing bicycle commuter user according to claim 1, wherein the process of performing secondary screening extraction on the primary sharing bicycle effective data in the time dimension is as follows:
the method comprises the steps of taking a user with the number of days of sharing bicycles being greater than or equal to 3 days in a working day of five days a week as an effective user, judging that corresponding one-time sharing bicycle effective data is effective, setting the accumulated number of days of sharing bicycles used in the working day of five days a week as t, wherein the date of sharing bicycle use is allowed to be discontinuous, the serial numbers of the sharing bicycles are allowed to be different, and judging:
if t is less than or equal to 2, rejecting the corresponding one-time sharing bicycle effective data;
and if t >2, extracting the corresponding primary sharing bicycle effective data and marking the primary sharing bicycle effective data as the secondary sharing bicycle effective data.
6. The method for identifying occupation type of sharing bicycle commuter user according to claim 1, wherein the process of performing three-time screening extraction on the effective data of the secondary sharing bicycle in the space dimension is as follows:
identifying and classifying all possible riding terminal point data of a certain destination of any effective user, calculating the distances between all the riding terminal points of the user by using space coordinate data for any user, performing cluster analysis by taking the distances as parameters, and outputting all possible riding terminal point position data of each destination of any user;
if the number of different date labels in all possible riding endpoint data of a certain destination of any effective user exceeds half of the accumulated use days of the user, the destination is used as one of possible candidate working sites of the user;
identifying the candidate working place with the largest amount of possible riding terminal data as the most possible working place, counting the amount of the riding terminal data contained in the possible working place of the user and all the possible riding terminal data of the user, extracting the destination with the largest riding terminal amount as the most possible working place of the user, extracting the corresponding secondary sharing bicycle effective data and marking the secondary sharing bicycle effective data as the tertiary sharing bicycle effective data.
7. The method of claim 6, wherein if a plurality of the same maximum values occur for the possible work sites and the number of all possible riding end points of the user, the sum of distances between the candidate work sites corresponding to all possible riding end points is compared, and the candidate work site with the smallest sum of distances is used as the most likely work site of the user.
8. A method of identifying occupation types of shared bicycle commuting users as claimed in claim 1, wherein the decision area of the user's occupation type is defined as follows:
calculating the maximum tolerable walking distance r from the parking point/riding end point D to the destination, namely the maximum walking radius, calculating the distance between the riding end point of the shared bicycle and the nearest neighbor POI data around the riding end point, drawing a maximum walking radius-shared bicycle data volume ratio histogram, and adaptively determining the value of the maximum tolerable walking distance from the parking point/riding end point to the destination, wherein the following two conditions are simultaneously satisfied:
in a circular area taking a riding end point of the shared bicycle as a circle center and r as a radius, at least 1POI data can be inquired;
the shared bicycle data satisfying the above condition accounts for 90% of the total shared bicycle data;
for all possible riding endpoints of any most likely workplace, centering on one riding endpoint from parking spot/riding endpoint DThe maximum tolerable walking distance r to the destination is taken as a radius, the walking reachable range based on the actual road network is calculated, and then the walking reachable ranges of all riding terminals are fused, so that the walking reachable range is taken as a decision area A of the occupation type of the shared bicycle user d 。
9. A method of identifying occupation types of shared bicycle commuting users as claimed in claim 1 wherein the process of identifying the user's occupation type is as follows:
combining a basic formula of a gravity model, comprehensively considering factors influencing the occupation type of a user, and determining variables involved in operation, including distance, type specific gravity and environment, wherein the distance is calculated in a decision area A d Average distance between a certain POI and each riding endpoint in any effective cluster group; the calculation mode of the type proportion is decision area A d The ratio of the number of POIs mapped to a certain professional type to the number of POIs mapped to an professional type throughout the investigation region; the computing mode of the environment is decision area A d The ratio of any one of the occupational type gravities to the sum of the 5 occupational type gravities is as follows:
wherein t is ij For P i And P j Population, d, of cells i and j, respectively ij The distance between the cells i and j is given, and k is a model parameter; ρ is the type specific gravity, number (importation) i ) For the number of POIs in a decision area of a user mapped to a certain professional type,sum(occupation i ) Mapping the whole decision area to the number of POIs of the job type; c is an environmental parameter, ρ (occupancy) i ) For a type specific gravity of a certain professional type in a decision area of a certain user,a type specific gravity sum of 5 occupation types in a decision area of a certain user;
the method comprises the steps that the effective sharing riding terminal data of a certain user is combined with POI data, and the probability that the user is a professional technician, a clerk and related personnel, a business service personnel, a production and transportation equipment operator and related personnel, and agricultural, forest, pasture, fishing and aquatic production personnel are measured one by using a gravity model; and calculating the normalization probability of the user for the job types by using a Bayesian rule, taking the job type corresponding to the highest value of the normalization probability as the job type of the user, and outputting a recognition result, wherein the formula is as follows:
wherein G (D, P i ) For the probability that a user is of a certain professional type,an average distance between a POI and all possible riding endpoints most likely to be destination at the work site within a user's decision area; p (P) r (P i I D) normalized probability that a user is of a certain professional type, ++>Probability of 5 occupation types for a user, respectivelyAnd;
if the normalized probability of 2 or more occupation types of a certain user is the same, comparing the absolute values of single parameters according to the sequence of distance, type proportion and environment, taking the occupation type with the largest absolute value as the final occupation type of the user, and when the distance parameter maximum value of 2 or more occupation types is the same, comparing the absolute values of the type proportion parameters, and the like.
10. A system for identifying occupation types of shared bicycle commuter users, comprising:
and a data processing module: the method comprises the steps of receiving POI data, urban road network data and shared bicycle data, and cleaning and screening the shared bicycle data to obtain shared bicycle effective data;
and a primary screening module: the method comprises the steps of calculating a normalization parameter of a user using the shared bicycle in a weekday peak, and carrying out primary screening extraction on effective data of the shared bicycle by using the normalization parameter of the user using the shared bicycle in the weekday peak to obtain primary effective data of the shared bicycle;
and a secondary screening module: the method comprises the steps of counting accumulated days of a user using a shared bicycle in a working day of a week, and carrying out secondary screening extraction on effective data of a primary shared bicycle in a time dimension to obtain effective data of a secondary shared bicycle;
and a third screening module: the method comprises the steps that the method is used for counting the end position of a shared bicycle used by a user on a week working day, and carrying out three-time screening extraction on effective data of a secondary shared bicycle in a space dimension to obtain effective data of the tertiary shared bicycle;
and an identification module: and the method is used for determining a decision area of the occupation type of the user according to the maximum walking radius and combining the urban road network data, judging the corresponding relation between the POI data and the occupation type, and identifying the occupation type of the user by utilizing the POI data and the three-time sharing bicycle effective data and combining the decision area of the occupation type of the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310910372.7A CN117056823A (en) | 2023-07-24 | 2023-07-24 | Method and system for identifying occupation type of shared bicycle commuter user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310910372.7A CN117056823A (en) | 2023-07-24 | 2023-07-24 | Method and system for identifying occupation type of shared bicycle commuter user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117056823A true CN117056823A (en) | 2023-11-14 |
Family
ID=88659916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310910372.7A Pending CN117056823A (en) | 2023-07-24 | 2023-07-24 | Method and system for identifying occupation type of shared bicycle commuter user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117056823A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252633A (en) * | 2023-11-20 | 2023-12-19 | 深圳联友科技有限公司 | Marketing method and system for workplace identification based on Internet of vehicles data |
| CN117612254A (en) * | 2023-11-23 | 2024-02-27 | 广州大学 | Shared bicycle commute behavior based identification method, system, equipment and medium |
-
2023
- 2023-07-24 CN CN202310910372.7A patent/CN117056823A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252633A (en) * | 2023-11-20 | 2023-12-19 | 深圳联友科技有限公司 | Marketing method and system for workplace identification based on Internet of vehicles data |
| CN117612254A (en) * | 2023-11-23 | 2024-02-27 | 广州大学 | Shared bicycle commute behavior based identification method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhong et al. | Inferring building functions from a probabilistic model using public transportation data | |
| Iqbal et al. | Development of origin–destination matrices using mobile phone call data | |
| CN102595323B (en) | Method for obtaining resident travel characteristic parameter based on mobile phone positioning data | |
| CN117056823A (en) | Method and system for identifying occupation type of shared bicycle commuter user | |
| CN108876475B (en) | City functional area identification method based on interest point acquisition, server and storage medium | |
| Graells-Garrido et al. | Inferring modes of transportation using mobile phone data | |
| Alfeo et al. | A stigmergy-based analysis of city hotspots to discover trends and anomalies in urban transportation usage | |
| Comi et al. | Private car OD flow estimation based on automated vehicle monitoring data: Theoretical issues and empirical evidence | |
| CN109101559A (en) | Urban functional area identification method based on POI and bus card swiping data | |
| Schönfelder et al. | Where do you want to go today?: More observations on daily mobility | |
| Zhang et al. | How road network transformation may be associated with reduced carbon emissions: An exploratory analysis of 19 major Chinese cities | |
| Cui et al. | Social media and mobility landscape: Uncovering spatial patterns of urban human mobility with multi source data | |
| Chen et al. | An analysis of movement patterns between zones using taxi GPS data | |
| Wang et al. | Exploring regional sustainable commuting patterns based on dockless bike-sharing data and POI data | |
| CN114511432A (en) | Digital country management service system based on block chain | |
| Bolaños-Martinez et al. | Clustering pipeline for vehicle behavior in smart villages | |
| CN112288472A (en) | Street planning demand identification method based on multi-source big data | |
| CN112699955A (en) | User classification method, device, equipment and storage medium | |
| CN112364776A (en) | Urban functional area recognition model establishing and classifying method and device | |
| Yue et al. | Classification and determinants of high-speed rail stations using multi-source data: A case study in Jiangsu Province, China | |
| Zhou et al. | Big data for intrametropolitan human movement studies A case study of bus commuters based on smart card data | |
| Crawford et al. | Analysing spatial intrapersonal variability of road users using point-to-point sensor data | |
| CN109508815B (en) | General activity spatial measure analysis method based on subway IC card data | |
| CN111833229B (en) | Subway dependency-based travel behavior space-time analysis method and device | |
| Michau | Link dependent origin-destination matrix estimation: nonsmooth convex optimisation with Bluetooth-inferred trajectories |
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 |