CN110020666B - Public transport advertisement putting method and system based on passenger behavior mode - Google Patents
Public transport advertisement putting method and system based on passenger behavior mode Download PDFInfo
- Publication number
- CN110020666B CN110020666B CN201910128113.2A CN201910128113A CN110020666B CN 110020666 B CN110020666 B CN 110020666B CN 201910128113 A CN201910128113 A CN 201910128113A CN 110020666 B CN110020666 B CN 110020666B
- Authority
- CN
- China
- Prior art keywords
- data
- passenger
- travel
- public transportation
- database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a public transportation advertisement putting method based on a passenger behavior mode, which comprises the steps of preprocessing acquired passenger data and constructing a passenger travel database; collecting data in the passenger travel database to form a vector related to passenger travel; clustering the vectors; dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2; and accurately delivering advertisements on public transportation according to the result of pattern recognition. The method can put advertisements in a targeted manner according to different requirements of passengers, improves the accuracy of advertisement putting and improves the utilization rate of advertisement resources.
Description
Technical Field
The invention relates to the technical field of processing of bus passenger data, in particular to a public transportation advertisement putting method and system based on a passenger behavior mode.
Background
For advertisers and operators of public transportation and passengers taking public transportation, the passengers hope to see accurately-put advertisements meeting the actual demands of the passengers on the public transportation, the passengers have better riding experience, and the advertisers and the operators of public transportation can improve the benefits of the passengers and achieve win-win of merchants and consumers.
The current bus advertisement putting is basically carried out in a mode of 'routing fixed part timing', merchants and advertisement companies negotiate advertisement putting lines, advertisement putting positions and advertisement putting time periods, and the selection of the putting lines and the putting time is basically based on the condition of line access stations and the size of passenger flow. The delivering mode has little effect and does not realize the complete utilization of resources. For example, with the continuous development of new media of the internet, the delivery amount of a variable LED electronic display screen, a vehicle-mounted television and the like in a bus system shows a greatly increasing trend, but the current lack of a targeted advertisement delivery mode makes the LED display screen and the vehicle-mounted television not really exert the due dynamic propaganda effect of the advertisement, but have little difference with the plane propaganda advertisement of a bus body. In addition, the travel prediction accuracy and timeliness of public transport passengers are not high at the present stage. Therefore, there is an urgent need in the industry to develop a method and system for predicting the travel of public transportation passengers based on the passenger behavior mode so as to target advertisement.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides a public transportation advertisement putting method based on a passenger behavior mode.
Another object of the present invention is to overcome the above-mentioned drawbacks of the prior art by providing a public transportation advertisement delivery system based on a passenger behavior pattern.
The aim of the invention is achieved by the following technical scheme:
a public transportation advertisement delivery method based on a passenger behavior mode, comprising:
s1, preprocessing acquired passenger data, and building a passenger travel database;
s2, collecting data in a passenger travel database to form a vector related to passenger travel;
s3, clustering the vectors;
s4, dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2;
s5, accurately delivering advertisements on public transportation according to the mode identification result.
Preferably, step S2 includes: extracting all data of the same card number from a database; the extracted data are all the trips of the passengers corresponding to the same card number; dividing all the travel of the passengers into N time periods to obtain travel times of each time period; and quantifying the travel times of each period to obtain a vector of the travel number of the passengers in the corresponding period.
Preferably, step S3 includes: and clustering the vectors based on a K-means clustering algorithm.
Preferably, the passenger data includes cardholder information, consumption information, boarding pass information, and boarding vehicle information.
Preferably, the step of preprocessing the collected passenger data further comprises: preprocessing and screening the acquired passenger data; the screened data comprise card numbers, card types, riding dates, riding time, riding routes and vehicle numbers.
Preferably, step S1 is preceded by: passenger data are collected through subway gates and/or passenger data are collected through bus cards taken into buses.
Preferably, step S1 is followed by: and predicting the acquired passenger data according to a shepherd interpolation prediction algorithm.
Preferably, between steps S1 and S2 comprises: when the newly acquired passenger data amount is greater than K, the newly acquired passenger data overlaps the passenger data in step S1.
Another object of the invention is achieved by the following technical scheme:
a public transportation advertisement delivery system based on a passenger behavior pattern, comprising: the system comprises a database construction module, a data processing module, a k-means clustering analysis module, a passenger behavior recognition module and an advertisement putting module which are connected in sequence; the database construction module is used for preprocessing the acquired passenger data and constructing a passenger travel database; the data processing module is used for gathering the data in the passenger travel database to form vectors related to passenger travel; the k-means cluster analysis module is used for clustering the vectors; the passenger behavior recognition module is used for dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2; and the advertisement putting module is used for accurately putting advertisements on public transportation according to the mode identification result.
Preferably, the data processing module comprises: a data extraction unit, a period division unit, and a quantization unit; the data extraction unit is used for extracting all data of the same card number in the database; the extracted data are all the trips of the passengers corresponding to the same card number; the time interval dividing unit is used for dividing all the travel of the passengers into N time intervals to obtain travel times of each time interval; and the quantization unit is used for quantizing the travel times of each period to obtain vectors of the travel number of passengers in the corresponding period.
Compared with the prior art, the invention has the following advantages:
the method comprises the steps of collecting data in a passenger travel database to form vectors related to passenger travel; clustering the vectors; dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2; according to the mode identification result, advertisements are put in a targeted manner according to different requirements of passengers, so that the accuracy of advertisement putting is improved, and the utilization rate of advertisement resources is improved; the type and time of advertisement delivery can be changed according to the needs of passengers or the change of the travel amount, which not only brings improvement of benefits to advertising companies and enterprises, but also meets the needs of the passengers.
In addition, the method also carries out accurate bus line passenger flow prediction of passenger types in time-sharing period according to the sheplate interpolation prediction algorithm, fully combines the factors of date such as workday property, school time property, holiday, weather and the like, has higher prediction precision and reliability and lower parameter dependence compared with the traditional neural network method and support vector machine method, thereby realizing the accuracy of advertisement delivery and providing a mode and method for the accurate prediction of the classification of passengers in public transportation.
Drawings
FIG. 1 is a flow chart of a public transportation advertising method based on a passenger behavior pattern of the present invention.
Fig. 2 is a schematic diagram of the structure of the public transportation advertisement delivery system based on the passenger behavior pattern of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples.
The invention discloses a public transportation advertisement putting method and a public transportation advertisement putting system based on a passenger behavior mode, which aim to improve the public transportation advertisement putting utilization rate, take the existing public transportation advertisement putting situation as the background, utilize the public transportation IC card swiping data of passengers, and adopt a passenger behavior mode identification and classification passenger flow prediction method based on cluster analysis to carry out accurate time-division passenger flow composition structure prediction and travel characteristic analysis. By using an accurate passenger flow prediction technology, the behavior modes of passengers are classified by using the card swiping data of the public transportation IC card, and then passenger flow compositions of each passenger type are predicted in a time-division manner, so that a targeted advertisement putting strategy can be formed, and the method can be used for improving service standards, perfecting driving specifications and the like, and finally achieving the aim of being beneficial to better configuration of traffic resources. For example, most of the passengers in the morning constitute commuter groups, advertisements such as fast-food, real estate, financial products and the like can be selectively put on the commuter groups, besides, the time value and opportunity cost of the commuter groups are high, and subway and bus operation companies can consider that schemes of reducing departure intervals and properly improving the speed of the passengers are adopted to meet the demands of the passengers.
Referring to fig. 1, a public transportation advertisement delivery method based on a passenger behavior mode includes:
s1, preprocessing acquired passenger data, and building a passenger travel database; the passenger data includes cardholder information, consumption information, route information, and vehicle information. The step of preprocessing the collected passenger data further comprises: preprocessing and screening the acquired passenger data; the screened data comprise card numbers, card types, riding dates, riding time, riding routes and vehicle numbers.
In this embodiment, the step S1 is preceded by: passenger data are collected through subway gates and/or passenger data are collected through bus cards taken into buses.
S2, collecting data in a passenger travel database to form a vector related to passenger travel; specifically, step S2 includes: extracting all data of the same card number from a database; the extracted data are all the trips of the passengers corresponding to the same card number; dividing all the travel of the passengers into N time periods to obtain travel times of each time period; and quantifying the travel times of each period to obtain a vector of the travel number of the passengers in the corresponding period. For example, a day may be divided into 8 time periods, and then a weekday may be distinguished from a holiday. And extracting all data of the same card number in the database, wherein the extracted data is all trips of a certain passenger in 5 months. And dividing all the travel of the passenger into 16 time periods of working days and holidays, so that the travel times of each time period are obtained. To cluster different passengers, we vectorize the travel records of each passenger. Each vector represents a passenger, and the vector has 16 elements, and each element represents (1 card-swiping times in the working day period, 2 card-swiping times in the working day period, 3 card-swiping times in the working day period, 4 card-swiping times in the working day period, 5 card-swiping times in the working day period, 6 card-swiping times in the working day period, 7 card-swiping times in the working day period, 8 card-swiping times in the working day period, 1 card-swiping times in the holiday period, 2 card-swiping times in the holiday period, 3 card-swiping times in the holiday period, 4 card-swiping times in the holiday period, 5 card-swiping times in the holiday period, 6 card-swiping times in the holiday period, 7 card-swiping times in the holiday period, and 8 card-swiping times in the holiday period) respectively.
In this embodiment, steps S1 and S2 include: when the newly acquired passenger data amount is greater than K, the newly acquired passenger data overlaps the passenger data in step S1.
S3, clustering the vectors; specifically, step S3 includes: and clustering the vectors based on a K-means clustering algorithm. The process of grouping a collection of physical or abstract objects into clusters of similar objects is referred to as clustering. Clusters generated by a cluster are a collection of data objects that are similar to objects in the same cluster, and are different from objects in other clusters. The K-means clustering algorithm solves the problem of dividing a set containing n data points (entities) into K class clusters. The algorithm firstly randomly selects k data points as initial cluster centers of k class clusters, and each data point in the set is divided into class clusters where the cluster centers closest to the data points are located, so that initial distribution of k clusters is formed. And calculating a new cluster center for each allocated cluster, and then continuing the data allocation process, wherein after the data are iterated for a plurality of times, if the cluster center is not changed any more, the data objects are all allocated to the cluster where the data object is located, and the clustering criterion function converges, otherwise, continuing the iteration process until the data are converged. The clustering criterion function here generally employs a cluster error squared sum criterion function. One characteristic of the K-means clustering algorithm is that the distribution of all data points is adjusted in each iteration process, then the cluster center is recalculated, the next iteration process is entered, if the positions of all data points are not changed in a certain iteration process, the corresponding cluster center is not changed, at the moment, the clustering criterion function is converged, and the algorithm is ended.
S4, dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2; after the kmeans clustering, the data are divided into a plurality of small clusters (data classes), then according to the characteristics of outputting each small cluster, each small class has own center vector, the mode identification of each classification is carried out through the investigation and simulation of experts and the evaluation group by combining the condition of the center vector of each small class, and after the classification, new clients added later (under the condition of lower database variation degree) are identified according to the Euclidean distance formula and are classified into the classified types. For example, the user category may be identified by observing the average center vector of the user in each cluster, deriving some basic features of the cluster, and analyzing the meaning that each of the parameters of these vectors represents. Firstly, carrying out qualitative analysis by combining existing data, obtaining a general analysis result by contacting professionals in related industries and departments and sampling investigation on the conditions of passengers in the field, then carrying out sampling investigation, obtaining a corresponding quantitative analysis result by filling out questionnaires, carrying out systematic processing and analysis on questions of questionnaire designs and basic information of filling-out persons, comprehensively carrying out quantitative analysis and qualitative analysis to obtain final pattern classification, and completing pattern recognition work. Finally, according to the identification result, the explanation and the explanation of each category are carried out through aspects of occupation characteristics, trip purpose, family composition, social status income level and the like, and the obtained data are used for later analysis, expansion and development work.
S5, accurately delivering advertisements on public transportation according to the mode identification result.
In the present embodiment, step S1 is followed by: and predicting the acquired passenger data according to a shepherd interpolation prediction algorithm. The main idea of the algorithm model construction is as follows: firstly, extracting attributes related to the date and the passenger flow, quantifying and normalizing the attributes, and establishing a multidimensional attribute matrix aiming at the date; secondly, evaluating the correlation and sensitivity between each attribute and passenger flow, extracting the dimension of effective prediction, and weighting each effective dimension; thirdly, predicting the time period passenger flow of the target date by using a sheplate interpolation prediction algorithm in the preprocessed attribute matrix on the basis of historical data; and finally, carrying out quality evaluation on the prediction result. The prediction method is more accurate and has better inefficacy and prediction rationality than the traditional statistical prediction method. The traditional statistical prediction method simply analyzes the passenger flow law from the data statistics angle, and further performs statistical prediction, and the prediction quality depends on the statistical data quality to a great extent, so that the method has low precision and low reliability. The traditional machine learning prediction method improves prediction precision and reliability, but has the defects of complex model, large parameter dependence, high dependence on training data quality and the like. The interpolation prediction method is also a widely applied prediction method, and has the advantages of high precision and small parameter dependence. Meanwhile, the interpolation prediction method has preliminary research on traffic flow prediction and obtains a certain result, and different conditions such as holidays, time periods, academic hours, air temperatures, extreme weather and the like have different influence degrees on different passenger flows and different people with travel characteristics, which are functions which are not possessed by mature prediction models of time sequence analysis and the like, and only through a multidimensional interpolation prediction algorithm, the obtained passenger flows of time-division and type-division can be more accurate, and the method is more in line with the reality.
Referring to fig. 2, the public transportation advertisement delivery system based on the passenger behavior pattern, to which the public transportation advertisement delivery method based on the passenger behavior pattern is applicable, includes: the system comprises a database construction module, a data processing module, a k-means clustering analysis module, a passenger behavior recognition module and an advertisement putting module which are connected in sequence; the database construction module is used for preprocessing the acquired passenger data and constructing a passenger travel database; the data processing module is used for gathering the data in the passenger travel database to form vectors related to passenger travel; the k-means cluster analysis module is used for clustering the vectors; the passenger behavior recognition module is used for dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2; and the advertisement putting module is used for accurately putting advertisements on public transportation according to the mode identification result.
In this embodiment, the data processing module includes: a data extraction unit, a period division unit, and a quantization unit; the data extraction unit is used for extracting all data of the same card number in the database; the extracted data are all the trips of the passengers corresponding to the same card number; the time interval dividing unit is used for dividing all the travel of the passengers into N time intervals to obtain travel times of each time interval; and the quantization unit is used for quantizing the travel times of each period to obtain vectors of the travel number of passengers in the corresponding period.
The above embodiments are preferred examples of the present invention, and the present invention is not limited thereto, and any other modifications or equivalent substitutions made without departing from the technical aspects of the present invention are included in the scope of the present invention.
Claims (6)
1. A public transportation advertisement delivery method based on a passenger behavior mode, comprising:
s1, preprocessing acquired passenger data, and building a passenger travel database;
s2, collecting data in a passenger travel database to form a vector related to passenger travel;
s3, clustering the vectors;
s4, dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2;
s5, accurately putting advertisements on public transportation according to the mode identification result;
the step S1 is followed by:
predicting the acquired passenger data according to a shepherd interpolation prediction algorithm;
the step S2 comprises the following steps:
extracting all data of the same card number from a database; the extracted data are all the trips of the passengers corresponding to the same card number;
dividing all the travel of the passengers into N time periods to obtain travel times of each time period;
quantifying the travel times of each period to obtain a vector of the travel number of the passengers in the corresponding period;
the step S3 comprises the following steps:
and clustering the vectors based on a K-means clustering algorithm.
2. The method of public transportation advertising based on passenger behavior patterns according to claim 1, wherein the passenger data includes cardholder information, consumption information, route information and vehicle information.
3. The method for advertising public transportation based on passenger behavior patterns according to claim 2, wherein the step of preprocessing the collected passenger data further comprises:
preprocessing and screening the acquired passenger data; the screened data comprise card numbers, card types, riding dates, riding time, riding routes and vehicle numbers.
4. The public transportation advertisement delivery method based on the passenger behavior pattern according to claim 1, wherein before step S1, comprising:
passenger data are collected through subway gates and/or passenger data are collected through bus cards taken into buses.
5. The method for advertising public transportation based on passenger behavior patterns according to claim 1, wherein between steps S1 and S2 comprises:
when the newly acquired passenger data amount is greater than K, the newly acquired passenger data overlaps the passenger data in step S1.
6. A public transportation advertisement delivery system based on a passenger behavior pattern, comprising: the system comprises a database construction module, a data processing module, a k-means clustering analysis module, a passenger behavior recognition module and an advertisement putting module which are connected in sequence;
the database construction module is used for preprocessing the acquired passenger data and constructing a passenger travel database;
the data processing module is used for gathering the data in the passenger travel database to form vectors related to passenger travel;
the k-means cluster analysis module is used for clustering the vectors;
the passenger behavior recognition module is used for dividing clustered data into N data classes, and carrying out pattern recognition on each data class through investigation and simulation according to the center vector of each data class; n is more than or equal to 2;
the advertisement putting module is used for accurately putting advertisements on public transportation according to the mode identification result;
after preprocessing the acquired passenger data and building a passenger travel database, the method comprises the following steps: predicting the acquired passenger data according to a shepherd interpolation prediction algorithm;
the data processing module comprises: a data extraction unit, a period division unit, and a quantization unit;
the data extraction unit is used for extracting all data of the same card number in the database; the extracted data are all the trips of the passengers corresponding to the same card number;
the time interval dividing unit is used for dividing all the travel of the passengers into N time intervals to obtain travel times of each time interval;
and the quantization unit is used for quantizing the travel times of each period to obtain vectors of the travel number of passengers in the corresponding period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128113.2A CN110020666B (en) | 2019-02-21 | 2019-02-21 | Public transport advertisement putting method and system based on passenger behavior mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128113.2A CN110020666B (en) | 2019-02-21 | 2019-02-21 | Public transport advertisement putting method and system based on passenger behavior mode |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110020666A CN110020666A (en) | 2019-07-16 |
| CN110020666B true CN110020666B (en) | 2023-06-20 |
Family
ID=67189036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910128113.2A Active CN110020666B (en) | 2019-02-21 | 2019-02-21 | Public transport advertisement putting method and system based on passenger behavior mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110020666B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533483A (en) * | 2019-09-05 | 2019-12-03 | 中国联合网络通信集团有限公司 | A kind of occupant classification method and system based on trip characteristics |
| CN110956505B (en) * | 2019-12-04 | 2021-03-16 | 腾讯科技（深圳）有限公司 | Advertisement inventory estimation method and related device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012088871A (en) * | 2010-10-19 | 2012-05-10 | Hitachi Solutions Ltd | Advertisement distribution system in means of public transportation |
| CN104063801B (en) * | 2014-06-23 | 2016-05-25 | 有米科技股份有限公司 | A kind of moving advertising recommend method based on cluster |
| CN104217129B (en) * | 2014-09-22 | 2018-02-02 | 北京交通大学 | A kind of urban rail road network passenger flow evaluation method |
| CN105718946A (en) * | 2016-01-20 | 2016-06-29 | 北京工业大学 | Passenger going-out behavior analysis method based on subway card-swiping data |
| CN106951976B (en) * | 2016-10-12 | 2021-09-21 | 华南理工大学 | Bus passenger flow prediction method based on mode classification |
| KR101926807B1 (en) * | 2016-11-30 | 2018-12-07 | 동의대학교 산학협력단 | System and Method for Transmitting target advertisement based on Customer in Public transportation |
| CN108171970A (en) * | 2017-12-11 | 2018-06-15 | 北京奇虎科技有限公司 | A kind of method and device for obtaining passenger on public transport track |
| CN108171533B (en) * | 2017-12-11 | 2021-07-23 | 北京奇虎科技有限公司 | Vehicle-mounted advertisement bus route recommendation method and device based on intelligent bus card data |
-
2019
- 2019-02-21 CN CN201910128113.2A patent/CN110020666B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110020666A (en) | 2019-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062857B (en) | Prediction technique for cab-getter's trip purpose | |
| CN107633035B (en) | Shared traffic service reorder estimation method based on K-Means and LightGBM model | |
| CN112949926B (en) | Income maximization ticket amount distribution method based on passenger demand re-identification | |
| CN111291236A (en) | Expressway network user image information acquisition and analysis method and system | |
| CN110084505A (en) | A kind of smart shift scheduling method and device based on passenger flow, mobile end equipment, server | |
| CN111598333B (en) | Passenger flow data prediction method and device | |
| CN107274066B (en) | LRFMD model-based shared traffic customer value analysis method | |
| CN110020666B (en) | Public transport advertisement putting method and system based on passenger behavior mode | |
| CN110889092A (en) | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data | |
| CN109191181B (en) | Digital signage advertisement audience and crowd classification method based on neural network and Huff model | |
| Li et al. | Using smart card data trimmed by train schedule to analyze metro passenger route choice with synchronous clustering | |
| CN112116810A (en) | Whole road network segment travel time estimation method based on urban road checkpoint data | |
| Ma et al. | Public transportation big data mining and analysis | |
| Chen et al. | RFM Model and K‐Means Clustering Analysis of Transit Traveller Profiles: A Case Study | |
| CN111582738A (en) | Method for predicting aviation passenger flow demand of regional airport group | |
| CN117436653A (en) | Prediction model construction method and prediction method for travel demands of network about vehicles | |
| CN111241162A (en) | Method for analyzing travel behaviors of passengers under high-speed railway network formation condition and storage medium | |
| Basu | Data-driven customer segmentation and personalized information provision in public transit | |
| CN112836996B (en) | Method for identifying potential ticket buying demand of passenger | |
| CN113449780B (en) | Intra-road berth occupancy prediction method based on random forest and LSTM neural network | |
| Ruch et al. | The impact of fleet coordination on taxi operations | |
| CN112052898B (en) | Construction method and system for potential classification model of intercity high-speed rail passenger | |
| Ku et al. | Trip-pair based clustering model for urban mobility of bus passengers in Macao | |
| Nagy et al. | Land-use zone estimation in public transport planning with data mining | |
| CN114119314A (en) | Urban network comprehensive analysis method and system based on multi-source element flow |
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 |